© 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. 78664
    Prev
    Next
    INDEX
    Explanations

    positive reviews or comments

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

    extract function

    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
    ме
    0.53
    на
    0.44
    бі
    0.44
    бе
    0.43
    な
    0.43
     ஸ
    0.42
    мани
    0.41
    ステ
    0.41
    enb
    0.41
     उमर
    0.41
    POSITIVE LOGITS
    rogram
    0.45
    ພວກເຮ
    0.44
    LLAR
    0.43
     khuôn
    0.42
    켓
    0.42
    /');
    0.42
    폐
    0.41
    '])->
    0.40
     القص
    0.40
    ;');
    0.40
    Activations Density 0.000%

    No Known Activations