© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 88
    Prev
    Next
    INDEX
    Explanations

    file paths 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
    我們的
    -1.93
    慊
    -1.75
    ਲ਼
    -1.74
    谞
    -1.74
    盦
    -1.70
    меч
    -1.66
     Polícia
    -1.57
    чены
    -1.57
     kellett
    -1.57
     klienta
    -1.55
    POSITIVE LOGITS
    </h2>
    2.31
    _
    2.06
     trotz
    2.02
     /
    1.89
    the
    1.83
    red
    1.74
    see
    1.73
    /
    1.71
    </strong>
    1.66
     who
    1.64
    Activations Density 0.003%

    No Known Activations