© 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. 20340
    Prev
    Next
    INDEX
    Explanations

    first, second, third

    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
    颪
    -1.56
    ではなく
    -1.49
    </strong>
    -1.48
    餮
    -1.44
     créé
    -1.39
    zzet
    -1.34
    THING
    -1.31
    Esperamos
    -1.30
     الجزء
    -1.29
    躡
    -1.28
    POSITIVE LOGITS
     there
    1.91
     first
    1.80
     and
    1.52
     those
    1.52
    ｅ
    1.48
     on
    1.43
     at
    1.42
    。
    1.41
    ."
    1.36
    '
    1.34
    Activations Density 0.116%

    No Known Activations