© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74006
    Prev
    Next
    INDEX
    Explanations

    forge a course or path

    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
    鹀
    -1.55
     télévisée
    -1.55
    ⽌
    -1.55
    //.
    -1.52
    !";
    -1.48
     Verständ
    -1.48
    }$
    -1.45
     ³
    -1.44
     '?'
    -1.44
    <code>
    -1.43
    POSITIVE LOGITS
     through
    2.03
     into
    1.64
     for
    1.63
     path
    1.53
     also
    1.52
    řízen
    1.47
     towards
    1.45
    但这
    1.45
     größere
    1.43
     falou
    1.43
    Activations Density 0.019%

    No Known Activations