© 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. 91295
    Prev
    Next
    INDEX
    Explanations

    reporting time periods and durations

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

    repr.a

    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
    B
    0.61
    W
    0.61
    l
    0.60
    V
    0.59
    uo
    0.57
     presa
    0.56
    X
    0.54
    F
    0.54
    ST
    0.53
    m
    0.53
    POSITIVE LOGITS
     таке
    0.48
     అని
    0.47
     வாழ்க்க
    0.46
    仪式
    0.45
     коронави
    0.45
    羞
    0.45
     ошиб
    0.45
    膦
    0.44
     నట
    0.44
    澹
    0.44
    Activations Density 0.001%

    No Known Activations