© 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. 15331
    Prev
    Next
    INDEX
    Explanations

    CSS and JavaScript usage

    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
    řejmě
    -1.03
    indows
    -1.00
    istible
    -0.97
    ,
    -0.94
     шей
    -0.92
    lasses
    -0.90
    ₇
    -0.88
    పు
    -0.88
    apatkan
    -0.86
    UTER
    -0.85
    POSITIVE LOGITS
     normally
    1.00
     default
    0.99
     already
    0.94
     cristi
    0.93
    noticed
    0.92
     вже
    0.92
     bianche
    0.91
    強調
    0.87
     existing
    0.85
     noticed
    0.85
    Activations Density 0.072%

    No Known Activations