© 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. 10-GEMMASCOPE-RES-131K
    7. 40790
    Prev
    Next
    INDEX
    Explanations

    stipulated conditions

    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_10/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
    铪
    -2.41
    鳔
    -2.30
     Atención
    -2.25
    ſters
    -2.23
     praktische
    -2.20
    禵
    -2.19
     novelist
    -2.19
     ウィメンズ
    -2.13
     \%
    -2.11
     Onder
    -2.09
    POSITIVE LOGITS
    u
    2.72
    on
    2.67
    n
    2.59
     stipulated
    2.36
    i
    2.31
    EN
    2.28
    up
    2.27
    m
    2.25
    .”
    2.25
    ID
    2.25
    Activations Density 0.001%

    No Known Activations