© 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. 126821
    Prev
    Next
    INDEX
    Explanations

    specific abbreviations with following details

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

    contrast or exception

    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
    n
    0.77
    de
    0.64
    sim
    0.62
    nn
    0.62
    sw
    0.61
    K
    0.61
    st
    0.59
    V
    0.59
    nik
    0.59
    （
    0.57
    POSITIVE LOGITS
     convulsions
    0.61
     poisons
    0.54
     giảng
    0.52
     urges
    0.49
     poisoning
    0.49
     clearances
    0.48
     playlists
    0.48
     choline
    0.47
     precepts
    0.47
     bloated
    0.47
    Activations Density 0.000%

    No Known Activations