© 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. 240553
    Prev
    Next
    INDEX
    Explanations

    word followed by punctuation

    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
     SOUND
    0.50
     называется
    0.46
     Promo
    0.45
    ="
    0.45
    ु
    0.45
    mael
    0.44
     AND
    0.44
     SS
    0.44
    onymous
    0.43
    '{
    0.43
    POSITIVE LOGITS
     integrals
    0.54
     haircuts
    0.50
     inaccuracies
    0.48
     incandescent
    0.48
     interruptions
    0.47
     altas
    0.47
     autocorrelation
    0.47
    infrared
    0.46
     trovare
    0.46
    actively
    0.45
    Activations Density 0.000%

    No Known Activations