© 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. 84412
    Prev
    Next
    INDEX
    Explanations

    with whom

    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
     of
    -2.39
     then
    -2.22
    了一個
    -1.77
    が上が
    -1.73
    我还是
    -1.63
    本番
    -1.59
    还是要
    -1.55
    鸰
    -1.53
    我才
    -1.52
     following
    -1.52
    POSITIVE LOGITS
    他
    1.86
    ۳
    1.68
    !'
    1.63
    ldots
    1.55
    ۷
    1.50
    ну
    1.49
    一切
    1.49
     exacta
    1.48
    ʁ
    1.47
     she
    1.46
    Activations Density 0.034%

    No Known Activations