© 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. 7562
    Prev
    Next
    INDEX
    Explanations

    affiliate links or error stating

    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
    着一个
    -1.79
    na
    -1.48
    着一
    -1.45
    ⊆
    -1.39
    着自己的
    -1.38
    遊ぶ
    -1.37
    beit
    -1.34
     into
    -1.34
    commonly
    -1.30
    jść
    -1.29
    POSITIVE LOGITS
     on
    1.91
     with
    1.88
     you
    1.66
     that
    1.66
     by
    1.62
     and
    1.59
     any
    1.52
    cepat
    1.49
     specially
    1.45
    Inggris
    1.45
    Activations Density 0.253%

    No Known Activations