© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31905
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens (digits and numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical programming/code tokens—especially class or method identifiers, namespaces, and related software terms in code or configuration contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    tokens that appear in technical documentation or code, particularly in structured formats like XML, configuration files, or programming syntax.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Payer
    -0.77
    puppy
    -0.75
     COS
    -0.74
     obti
    -0.73
    }?>
    -0.73
    Противо
    -0.73
    olingo
    -0.71
    carved
    -0.71
     INSERT
    -0.70
     Nia
    -0.70
    POSITIVE LOGITS
    rago
    0.85
    atschapp
    0.78
     spodnie
    0.78
     вули
    0.77
    aini
    0.75
    λαμβ
    0.74
    rinas
    0.74
    setViewport
    0.74
    ılmıştır
    0.73
    Clamp
    0.73
    Activations Density 0.000%

    No Known Activations