© 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. 73105
    Prev
    Next
    INDEX
    Explanations

    teaser sentences

    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
     pero
    -2.44
    ");
    -2.42
     nhưng
    -2.30
    ῞
    -2.22
     You
    -2.17
     But
    -2.17
    ');
    -2.11
    你要
    -2.09
     AFTER
    -2.09
    屨
    -2.05
    POSITIVE LOGITS
    頃の
    2.64
    嗞
    2.19
    頃は
    2.14
    别的
    2.08
    antaranya
    2.03
     машине
    2.00
    全ての
    1.98
     cómod
    1.95
    錵
    1.92
     illogical
    1.91
    Activations Density 0.001%

    No Known Activations