© 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. 16189
    Prev
    Next
    INDEX
    Explanations

    fly, flying, flight

    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
    ↵
    -3.25
     .
    -3.03
    H
    -2.97
    S
    -2.92
    P
    -2.80
    R
    -2.59
    U
    -2.55
    O
    -2.38
     
    -2.36
    C
    -2.33
    POSITIVE LOGITS
     This
    3.20
    י
    2.73
     negociar
    2.67
    GillaGilla
    2.66
     مقالات
    2.66
     theses
    2.58
    驒
    2.55
    也
    2.53
     Tweede
    2.44
     مراسم
    2.42
    Activations Density 0.014%

    No Known Activations