© 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. 15317
    Prev
    Next
    INDEX
    Explanations

    numbers and letters forming identifiers

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

    words after '#'

    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
    </u>
    0.46
    .”
    0.42
    ~(\
    0.41
     Germ
    0.40
    JAK
    0.40
    اهده
    0.40
    Germ
    0.39
     Dark
    0.38
    wohner
    0.38
    .•
    0.37
    POSITIVE LOGITS
    </h1>
    0.44
     principalColumn
    0.41
    терна
    0.40
    РО
    0.39
     mainu
    0.39
    yczne
    0.39
    theoretic
    0.39
     bitOp
    0.39
     потер
    0.38
    ეცი
    0.38
    Activations Density 0.000%

    No Known Activations