© 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. 73206
    Prev
    Next
    INDEX
    Explanations

    final or last item in a series

    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
     because
    -1.95
     використання
    -1.82
    Being
    -1.81
    Surprisingly
    -1.76
    Recently
    -1.73
    Other
    -1.70
     Якщо
    -1.66
     using
    -1.65
    袮
    -1.63
    During
    -1.63
    POSITIVE LOGITS
    </sup>
    2.03
    ulaski
    1.73
    z
    1.73
    </td>
    1.69
    </h2>
    1.68
    力
    1.68
    tieve
    1.67
     —
    1.66
    thansa
    1.65
    ':{'
    1.64
    Activations Density 0.026%

    No Known Activations