© 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. 71097
    Prev
    Next
    INDEX
    Explanations

    advisory board, committee, council, roles

    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
    縢
    -2.64
    很多的
    -2.38
     trough
    -2.33
     mumbled
    -2.30
     principalmente
    -2.25
    ꜆
    -2.25
     プリント
    -2.20
    毳
    -2.19
     trock
    -2.16
     albeit
    -2.11
    POSITIVE LOGITS
    .
    2.53
    袮
    2.38
    We
    2.34
    You
    2.28
    你
    2.25
    Our
    2.23
    Name
    2.22
    狆
    2.17
    up
    2.13
    ۹
    2.05
    Activations Density 0.010%

    No Known Activations