© 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. 22-GEMMASCOPE-RES-131K
    7. 14255
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

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

    The neuron is detecting numeric constants (integer or floating‐point literals) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    屡
    -0.84
     būtų
    -0.82
     to
    -0.82
    しては
    -0.81
     ambass
    -0.81
    Kitty
    -0.78
     enchantment
    -0.78
     repug
    -0.77
     conquests
    -0.77
     jubile
    -0.77
    POSITIVE LOGITS
     this
    0.87
     lagi
    0.84
    こちらは
    0.84
     hugely
    0.84
    Şi
    0.82
     hice
    0.81
    ologiques
    0.79
    }],
    0.78
    conhe
    0.77
    urangi
    0.76
    Activations Density 0.003%

    No Known Activations