© 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. 10-GEMMASCOPE-RES-131K
    7. 73333
    Prev
    Next
    INDEX
    Explanations

    .aspx

    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
    S
    -3.30
    (
    -3.09
    M
    -3.08
    \
    -3.05
    L
    -2.98
    ar
    -2.94
    B
    -2.83
    of
    -2.81
    P
    -2.80
    K
    -2.64
    POSITIVE LOGITS
    ’
    3.17
    𖣔
    2.69
     этот
    2.58
     эти
    2.36
     huéspedes
    2.34
    嵎
    2.33
    sandalia
    2.23
    穑
    2.22
    ㉗
    2.19
     untuk
    2.16
    Activations Density 0.003%

    No Known Activations