© 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. 22-GEMMASCOPE-RES-131K
    7. 65844
    Prev
    Next
    INDEX
    Explanations

    AD to RULEhouse is 4, f inal

    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_22/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
    masa
    -0.83
     information
    -0.79
     jantung
    -0.78
    郵
    -0.76
     ”
    -0.75
    orenje
    -0.75
    Remaining
    -0.73
     if
    -0.73
    ؤول
    -0.73
     соответствии
    -0.73
    POSITIVE LOGITS
     illustre
    0.90
    Válasz
    0.90
     allerlei
    0.88
    ESOME
    0.88
     devraient
    0.87
     分享
    0.87
    weiterlesen
    0.87
    יקה
    0.85
     αγα
    0.85
     $,
    0.84
    Activations Density 0.031%

    No Known Activations