© 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. 39441
    Prev
    Next
    INDEX
    Explanations

    providing solutions or help

    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
     appr
    0.48
     тех
    0.43
    _{
    0.43
     より
    0.42
    relu
    0.41
    ',\
    0.41
     those
    0.40
    <unused61>
    0.40
     個
    0.40
     至
    0.40
    POSITIVE LOGITS
    אַר
    0.45
    летний
    0.43
    Tickets
    0.42
     Vitória
    0.42
    сур
    0.42
     ٹرسٹ
    0.41
    决心
    0.41
    фия
    0.41
     ভাতা
    0.40
    압
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.