© 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. 65331
    Prev
    Next
    INDEX
    Explanations

    parts of names and place names

    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
    !
    -1.81
    /
    -1.73
     both
    -1.62
    -
    -1.62
     not
    -1.58
     only
    -1.52
    .
    -1.51
     just
    -1.48
    '
    -1.48
     all
    -1.43
    POSITIVE LOGITS
    fordshire
    2.20
    ckeye
    2.00
    ledad
    1.84
    ifornia
    1.79
    moiselle
    1.75
    ificantly
    1.63
    thodox
    1.63
    cky
    1.61
    viate
    1.61
    tuce
    1.60
    Activations Density 0.096%

    No Known Activations