© 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. 194612
    Prev
    Next
    INDEX
    Explanations

    sentence structure indicators

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

    consult, contribute, oracle, scavenger

    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
     سپورټ
    0.45
    وقع
    0.44
    لم
    0.44
    لي
    0.44
    ేక
    0.43
     mobilization
    0.43
     sustenance
    0.42
    ">)</
    0.42
    .),
    0.42
     fractionation
    0.41
    POSITIVE LOGITS
    ligi
    0.62
    '*
    0.55
     यंत्र
    0.54
     Maserati
    0.54
    '^
    0.52
     企业
    0.51
    ?
    0.51
    '?
    0.50
     Instagram
    0.49
    (
    0.49
    Activations Density 0.000%

    No Known Activations