© 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. 84286
    Prev
    Next
    INDEX
    Explanations

    /service logs

    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
     we
    -2.33
    我們
    -2.06
    我们
    -1.96
     of
    -1.79
     our
    -1.78
    </em>
    -1.78
     for
    -1.74
    ֺ
    -1.74
     atau
    -1.72
    ᐈ
    -1.63
    POSITIVE LOGITS
     encender
    1.95
    銓
    1.84
    謚
    1.69
    וּ
    1.69
    Цитата
    1.67
    憚
    1.66
     廠
    1.66
    voici
    1.63
    itized
    1.63
     permitirá
    1.63
    Activations Density 0.170%

    No Known Activations