© 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. 78520
    Prev
    Next
    INDEX
    Explanations

    compelling arbitration and spam protection

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

    prey animals

    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
    0.55
     BS
    0.48
    BS
    0.45
    bs
    0.44
     <
    0.43
     Aaj
    0.43
     VAT
    0.42
    compl
    0.42
    difficulty
    0.42
     거기에
    0.42
    POSITIVE LOGITS
    лке
    0.48
     élargies
    0.47
    来看
    0.46
    apabb
    0.46
     সার্টিফি
    0.45
    т
    0.45
    人了
    0.45
    兰
    0.45
    мена
    0.44
     conducir
    0.44
    Activations Density 0.000%

    No Known Activations