© 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. 112361
    Prev
    Next
    INDEX
    Explanations

    introductions and descriptions

    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
    romeda
    -1.76
    andering
    -1.74
    −/−
    -1.60
     pakan
    -1.59
    tocks
    -1.59
     gerai
    -1.56
     tani
    -1.52
     dabar
    -1.52
    mmung
    -1.48
    iamo
    -1.48
    POSITIVE LOGITS
     for
    2.03
    It
    1.73
     who
    1.63
     sonriendo
    1.54
     What
    1.54
     ONLY
    1.54
     not
    1.51
     NOT
    1.46
     but
    1.45
     During
    1.43
    Activations Density 0.016%

    No Known Activations