© 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. 40410
    Prev
    Next
    INDEX
    Explanations

    latex graphicx and plotting

    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
    </h3>
    0.50
    </sub>
    0.49
     that
    0.48
     his
    0.47
     Bold
    0.46
    0.46
     precedent
    0.45
    印
    0.45
    ↵
    0.45
     and
    0.45
    POSITIVE LOGITS
     dyads
    0.54
    ციის
    0.51
     pathogenicity
    0.49
    Chiều
    0.47
    阉
    0.47
    oksatta
    0.46
     Physiol
    0.46
    ນິກ
    0.45
    <unused75>
    0.43
    ಬ್ಬಳ್ಳಿ
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.