© 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. 26215
    Prev
    Next
    INDEX
    Explanations

    championships, conferences, conventions, galas, meetings

    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
    X
    -1.74
    N
    -1.60
    J
    -1.59
    P
    -1.53
    Y
    -1.50
    b
    -1.50
    w
    -1.48
    q
    -1.48
    //
    -1.46
    v
    -1.46
    POSITIVE LOGITS
     in
    1.65
    lhe
    1.45
     at
    1.38
     biela
    1.37
     saine
    1.32
     paie
    1.29
     fuir
    1.28
     jugu
    1.27
    Inne
    1.27
     rése
    1.26
    Activations Density 0.048%

    No Known Activations