© 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. 73771
    Prev
    Next
    INDEX
    Explanations

    summary articles

    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
    {
    -4.19
     The
    -3.55
    2
    -3.42
     --
    -3.03
    }
    -2.89
    "
    -2.86
     you
    -2.78
    '
    -2.77
     "
    -2.77
     There
    -2.75
    POSITIVE LOGITS
    鋮
    2.92
    韪
    2.72
     bicicletas
    2.69
    年
    2.67
    ेमाल
    2.67
    縯
    2.63
    最后由
    2.61
    古风
    2.48
     शुर
    2.47
    趼
    2.47
    Activations Density 0.009%

    No Known Activations