© 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. 84827
    Prev
    Next
    INDEX
    Explanations

    stop by or come by

    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
    </em>
    -2.47
    0
    -2.22
    }{
    -2.16
    .
    -2.14
    which
    -2.02
    =
    -2.02
    ва
    -2.00
    ↵
    -1.93
    And
    -1.89
    9
    -1.88
    POSITIVE LOGITS
     unſ
    1.96
    廔
    1.90
    ޸
    1.89
    鉏
    1.87
    岀
    1.86
     飾り
    1.85
     assiste
    1.84
    🪐
    1.82
     太阳
    1.79
    😟
    1.77
    Activations Density 0.003%

    No Known Activations