© 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. 92909
    Prev
    Next
    INDEX
    Explanations

    Q: in vitro

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

    curly braces and syntax elements in programming code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric literals (number tokens) 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_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
     BitmapFactory
    -0.81
    参考にして
    -0.80
    rawa
    -0.73
     ulterior
    -0.72
     tendo
    -0.71
    divia
    -0.71
     zasad
    -0.70
     partake
    -0.70
    startAnimation
    -0.70
     DIAGRAM
    -0.69
    POSITIVE LOGITS
    Key
    1.03
    render
    0.99
    dataIndex
    0.98
     key
    0.96
    key
    0.96
     render
    0.93
    Render
    0.91
     Key
    0.87
    渲染
    0.82
    KEY
    0.77
    Activations Density 0.002%

    No Known Activations