© 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. 91084
    Prev
    Next
    INDEX
    Explanations

    events and activities

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

    Go to website instructions

    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
    Negative Logits
    g
    0.61
    et
    0.55
     DISCLAIMED
    0.54
     SUSY
    0.47
    ent
    0.47
     Planck
    0.46
    vis
    0.45
    dl
    0.45
    gesch
    0.45
     বাড়িয়ে
    0.45
    POSITIVE LOGITS
    Tub
    0.50
    ίναι
    0.48
    %","
    0.48
    ﻖ
    0.47
    ционе
    0.46
    %$
    0.45
     vair
    0.45
     artículo
    0.44
     Tub
    0.44
    定的
    0.44
    Activations Density 0.000%

    No Known Activations