© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189479
    Prev
    Next
    INDEX
    Explanations

    start of a sequence

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

    curses, game, law, insurance

    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
    c
    0.57
    un
    0.51
    ict
    0.51
    ix
    0.50
    ie
    0.49
    md
    0.49
     Http
    0.48
    it
    0.47
    uk
    0.47
    ign
    0.47
    POSITIVE LOGITS
     алюми
    0.62
     aviones
    0.56
    㡀
    0.55
     primeros
    0.53
     começou
    0.52
    تقاوى
    0.52
    䯩
    0.52
     commencé
    0.51
     தொடங்கியது
    0.51
     políticos
    0.50
    Activations Density 0.003%

    No Known Activations