© 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. 15668
    Prev
    Next
    INDEX
    Explanations

    UI selection components

    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
     a
    -1.47
    ğinde
    -1.20
    Abrir
    -0.97
     Grüßen
    -0.96
     både
    -0.96
    ategy
    -0.95
    fvar
    -0.93
     excused
    -0.93
    œuvres
    -0.92
    endurch
    -0.91
    POSITIVE LOGITS
    vail
    1.30
     нажмите
    1.18
    akyti
    1.08
    ଵ
    1.03
    complish
    1.02
    ırı
    1.01
    UTOR
    0.96
    phor
    0.95
    ()=>{
    0.95
     продол
    0.94
    Activations Density 0.032%

    No Known Activations