© 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. 15580
    Prev
    Next
    INDEX
    Explanations

    citations and parenthetical additions

    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
     sondern
    -1.02
     этих
    -0.98
     แต่
    -0.90
    appliquer
    -0.88
     คือ
    -0.86
    🎌
    -0.84
    badan
    -0.84
    ություն
    -0.84
     Iy
    -0.84
     Aufenthal
    -0.83
    POSITIVE LOGITS
     no
    0.88
     not
    0.85
    <em>
    0.85
     wobec
    0.85
    <i>
    0.84
     bawat
    0.84
     Gesicht
    0.83
    ndt
    0.82
     に関する
    0.82
     moldes
    0.82
    Activations Density 0.084%

    No Known Activations