© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15590
    Prev
    Next
    INDEX
    Explanations

    immediate consequence or follow-up

    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
     नवी
    0.52
    ча
    0.51
    RIE
    0.49
    ze
    0.49
    し
    0.47
    SYN
    0.45
    Syntax
    0.44
    e
    0.44
    as
    0.43
    VHS
    0.43
    POSITIVE LOGITS
     waarbij
    0.51
     moguć
    0.47
     tailles
    0.47
     waarin
    0.46
     komunik
    0.46
    袭
    0.46
     apprendre
    0.46
     Massimo
    0.45
     appartient
    0.45
    ᄈ
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.