© 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. 35111
    Prev
    Next
    INDEX
    Explanations

    close approach to nourishes

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

    violence, packs, payments, requested

    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
    G
    0.73
    V
    0.57
    hton
    0.56
    D
    0.54
    E
    0.53
    Little
    0.52
    P
    0.52
    International
    0.48
    я
    0.48
    countries
    0.48
    POSITIVE LOGITS
     فونبټ
    0.49
     proches
    0.48
     gonflement
    0.48
    व्यक्त
    0.47
     élargies
    0.47
     travailleurs
    0.47
     lésions
    0.47
    痞
    0.46
    膀
    0.46
     diferença
    0.46
    Activations Density 0.000%

    No Known Activations