© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63328
    Prev
    Next
    INDEX
    Explanations

    code, diagrams, or lists

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

    The neuron strongly activates on numeric tokens (e.g. numbers, numeric parameters, and related punctuation) in code snippets.

    oai_token-act-pair · o4-miniTriggered 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
    Condi
    -0.87
    ፍ
    -0.82
     міся
    -0.78
    すると
    -0.76
     purg
    -0.76
    𝘺
    -0.76
     ціка
    -0.75
    Steuer
    -0.75
    Frida
    -0.74
     interdependence
    -0.74
    POSITIVE LOGITS
    episode
    0.88
     widgets
    0.84
    ClientSize
    0.80
    Brother
    0.75
    モンスター
    0.74
    Pokud
    0.74
    čko
    0.73
    笼
    0.73
     Lynne
    0.73
     segment
    0.72
    Activations Density 0.011%

    No Known Activations