© 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. 15023
    Prev
    Next
    INDEX
    Explanations

    technical terms with descriptors

    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
    k
    -2.36
    r
    -2.27
    l
    -2.25
    p
    -2.19
    w
    -2.17
    m
    -2.16
    c
    -2.11
    g
    -2.08
    b
    -2.08
    h
    -2.03
    POSITIVE LOGITS
     Popis
    2.00
     teníamos
    1.95
     biela
    1.94
    katakan
    1.73
    logitech
    1.68
     nélk
    1.68
    indonesia
    1.66
    caucasian
    1.63
     that
    1.63
    bibit
    1.61
    Activations Density 0.136%

    No Known Activations