© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206436
    Prev
    Next
    INDEX
    Explanations

    green bins, artisan roast, former mayor

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

    data visualizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '||
    0.56
    '&&
    0.55
    abell
    0.48
     желательно
    0.46
    설
    0.46
    ॔
    0.46
    리스
    0.45
    する場合
    0.45
    irii
    0.45
    괄
    0.45
    POSITIVE LOGITS
    PED
    0.46
    ني
    0.46
     gravi
    0.45
    Kumar
    0.44
     PIL
    0.44
     نم
    0.41
     lmao
    0.41
     thang
    0.41
    Moving
    0.40
    嘢
    0.40
    Activations Density 0.001%

    No Known Activations