© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129933
    Prev
    Next
    INDEX
    Explanations

    town names and addresses

    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
    咴
    -2.55
    豈
    -2.41
    where
    -2.41
    ↵
    -2.30
    which
    -2.22
     poniendo
    -2.20
     dejando
    -1.99
     ambayo
    -1.98
    也得
    -1.95
    M
    -1.93
    POSITIVE LOGITS
    骉
    2.52
    玊
    2.39
    翃
    2.25
    enablog
    2.20
    蕷
    2.19
     we
    2.14
     einigen
    2.13
    udadera
    2.11
    私は
    2.09
    I
    2.08
    Activations Density 0.016%

    No Known Activations