© 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. 221130
    Prev
    Next
    INDEX
    Explanations

    Mueller and Muhlenburg

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

    mutulations

    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
    JMenuItem
    0.47
    wot
    0.47
    in
    0.46
    inį
    0.45
    Uint
    0.43
    HUN
    0.43
    usern
    0.42
    convén
    0.42
     bals
    0.41
    懋
    0.41
    POSITIVE LOGITS
     Mut
    0.86
     mut
    0.77
     MUT
    0.76
    Mut
    0.72
     Му
    0.69
     mú
    0.66
    mut
    0.64
     mutate
    0.63
     му
    0.62
     mutants
    0.62
    Activations Density 0.053%

    No Known Activations