© 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. 16351
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     (
    -1.04
     before
    -0.83
     裙
    -0.82
     aujourd
    -0.80
     verbringen
    -0.75
    northeast
    -0.74
    联系人
    -0.74
     Ihrem
    -0.74
     Roll
    -0.74
    usal
    -0.74
    POSITIVE LOGITS
     bigger
    0.93
     nuove
    0.88
     nuovi
    0.83
     Industria
    0.83
     majestic
    0.82
     bringe
    0.82
    טים
    0.81
     ステンレス
    0.81
    koa
    0.80
     PLW
    0.79
    Activations Density 0.036%

    No Known Activations