© 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. 93222
    Prev
    Next
    INDEX
    Explanations

    legal case names and software licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     from
    -0.86
    padek
    -0.83
    quium
    -0.83
    جي
    -0.82
    ifikation
    -0.82
     キャンペーン
    -0.81
     sekitarnya
    -0.81
    🧷
    -0.79
    شد
    -0.78
    ان
    -0.77
    POSITIVE LOGITS
    ciliation
    0.86
    Descriere
    0.85
     into
    0.79
    umd
    0.79
    ब्द
    0.75
     thereafter
    0.75
     attraverso
    0.74
    パンマン
    0.74
    そこは
    0.73
     времен
    0.72
    Activations Density 0.001%

    No Known Activations