© 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. 10-GEMMASCOPE-RES-131K
    7. 102397
    Prev
    Next
    INDEX
    Explanations

    court filings and proceedings

    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_10/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
     arbeta
    -1.82
     bermanfaat
    -1.66
    鈞
    -1.59
     bekerja
    -1.55
     กับ
    -1.55
     honnête
    -1.53
     Comprometido
    -1.52
     besök
    -1.52
     vissa
    -1.51
     skapa
    -1.51
    POSITIVE LOGITS
    .”
    1.82
     プレミアム
    1.59
     “
    1.56
     rather
    1.55
     мужа
    1.48
     itinéraires
    1.45
     been
    1.43
    还没有
    1.41
    也没有
    1.41
     somewhat
    1.39
    Activations Density 0.019%

    No Known Activations