© 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. 39744
    Prev
    Next
    INDEX
    Explanations

    will see

    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
    を使用した
    -1.73
    kệ
    -1.55
    {
    -1.45
    ⸨
    -1.44
    </h1>
    -1.44
    ⎘
    -1.41
     姜
    -1.40
    ortic
    -1.39
     tomas
    -1.38
    resulting
    -1.38
    POSITIVE LOGITS
    For
    1.83
    Also
    1.72
    This
    1.71
     also
    1.71
    In
    1.59
    見る
    1.59
    Another
    1.52
    我們的
    1.51
    Only
    1.49
    From
    1.44
    Activations Density 0.087%

    No Known Activations