© 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. 25349
    Prev
    Next
    INDEX
    Explanations

    http links and php files

    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
     yayınları
    -1.14
    meat
    -1.05
    jarse
    -1.04
     oyunu
    -1.02
    TextFormField
    -0.99
    역사
    -0.98
    棕色
    -0.97
     androidx
    -0.96
    İY
    -0.95
    ñera
    -0.95
    POSITIVE LOGITS
     have
    0.89
     &#
    0.88
    餒
    0.88
    釣
    0.86
    是怎么回事
    0.85
    泪
    0.84
    вій
    0.81
     Anliegen
    0.81
    .}(
    0.80
     diantaranya
    0.79
    Activations Density 0.024%

    No Known Activations