© 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. 10-GEMMASCOPE-RES-131K
    7. 43012
    Prev
    Next
    INDEX
    Explanations

    refinished, refinance, recirculation

    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
     concorda
    -2.89
     MUCH
    -2.77
    '
    -2.67
     are
    -2.53
     suporta
    -2.50
     conhece
    -2.42
     contém
    -2.41
    K
    -2.41
     WAY
    -2.36
     fazia
    -2.36
    POSITIVE LOGITS
    ولايات
    2.61
    釓
    2.48
     são
    2.48
     zog
    2.41
     outward
    2.38
    鐿
    2.36
    sonaro
    2.34
     jsou
    2.34
     этом
    2.28
     gritty
    2.22
    Activations Density 0.090%

    No Known Activations