© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6912
    Prev
    Next
    INDEX
    Explanations

    formal email subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     Wessex
    0.83
     airs
    0.78
    体に
    0.75
     Russell
    0.73
     Sudbury
    0.72
     Hats
    0.72
    ќ
    0.70
     Hatton
    0.70
    鄂
    0.70
     "/")
    0.69
    POSITIVE LOGITS
    LET
    1.10
    let
    1.08
     катего
    1.06
    lets
    1.03
     চলুন
    1.03
    letts
    1.00
    categorie
    0.99
    lán
    0.98
    zigzag
    0.97
    élix
    0.97
    Activations Density 0.003%

    No Known Activations