© 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. 72595
    Prev
    Next
    INDEX
    Explanations

    Ricky Gervais and other Rickys

    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
    end
    -2.34
    鲠
    -2.33
    d
    -2.23
     feiner
    -2.14
    內的
    -2.14
    pecabe
    -2.11
    isait
    -2.08
    were
    -2.06
    ological
    -2.06
    time
    -2.05
    POSITIVE LOGITS
     &#
    2.89
     第
    2.19
    幛
    2.13
    asants
    2.11
    nemer
    2.09
     Gator
    2.09
    ilà
    1.98
    梘
    1.98
    洐
    1.98
     Перейти
    1.97
    Activations Density 0.003%

    No Known Activations