© 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. 127763
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation preceding capitalized words

    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
     the
    -1.88
    部分を
    -1.68
    dlo
    -1.66
    avn
    -1.65
     acoged
    -1.53
      
    -1.53
     eve
    -1.48
    domés
    -1.47
    後記
    -1.46
     Possible
    -1.45
    POSITIVE LOGITS
    ’
    2.11
    eration
    1.69
     fiori
    1.61
     potranno
    1.60
     that
    1.60
     zijne
    1.58
    鈈
    1.55
    安卓
    1.54
    geſ
    1.54
    iſter
    1.53
    Activations Density 0.055%

    No Known Activations