© 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. 84436
    Prev
    Next
    INDEX
    Explanations

    give rise to

    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
    </i>
    -2.50
    </td>
    -2.34
     "
    -2.17
     the
    -2.08
    );
    -1.91
    甞
    -1.88
    使用的
    -1.87
    ’.”
    -1.87
    <b>
    -1.85
     uses
    -1.75
    POSITIVE LOGITS
    larımız
    1.86
     enviable
    1.84
    ㌧
    1.82
    侂
    1.81
    Étape
    1.78
    larım
    1.73
    larınız
    1.73
    يتها
    1.72
    。“
    1.71
    lardan
    1.70
    Activations Density 0.002%

    No Known Activations