© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89403
    Prev
    Next
    INDEX
    Explanations

    stitch around, collection by, leave your

    np_acts-logits-general · gemini-2.5-flash-lite

    grid, trading, mastery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clickView
    0.54
    敉
    0.54
     কলেরা
    0.54
    JORDAN
    0.53
    zieć
    0.52
    ości
    0.52
    deployRoot
    0.52
    𓈒
    0.52
    ैंड
    0.51
    أم
    0.51
    POSITIVE LOGITS
     in
    0.52
    0.48
     ie
    0.47
     triangle
    0.46
     MBA
    0.46
     *_
    0.45
     v
    0.45
     whichever
    0.45
    tsz
    0.45
    ’
    0.45
    Activations Density 0.000%

    No Known Activations