© 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. 99444
    Prev
    Next
    INDEX
    Explanations

    Q: or This

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

    The neuron is triggered by the kind of large, all-caps or CamelCase tokens you see in code headers and import blocks—especially software license and copyright comment lines.

    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
    mth
    -0.82
    oron
    -0.82
     ناح
    -0.75
     بدن
    -0.73
    児童
    -0.72
    ⓟ
    -0.72
    カメ
    -0.71
    ड़
    -0.71
    Bordeaux
    -0.69
     Lichten
    -0.69
    POSITIVE LOGITS
     prostate
    0.87
    sich
    0.86
    yscy
    0.84
    legi
    0.83
     تشکر
    0.82
    𝕣
    0.81
    мут
    0.81
    heatmap
    0.81
    vedev
    0.81
    resar
    0.81
    Activations Density 0.006%

    No Known Activations