© 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. 73141
    Prev
    Next
    INDEX
    Explanations

    `/#` or `*,` followed by code or URLs

    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
    <
    -2.94
    ’
    -2.66
    ↵
    -2.25
    ﹝
    -2.23
    <^
    -2.17
     公园
    -2.17
    以前的
    -2.14
    $
    -2.14
    勿論
    -2.09
     feiert
    -2.09
    POSITIVE LOGITS
    ться
    2.81
    o
    2.78
    or
    2.75
    ':
    2.70
    ;
    2.64
    l
    2.55
    就
    2.41
     '-':
    2.38
    }$
    2.19
    粁
    2.19
    Activations Density 0.006%

    No Known Activations