© 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. 6911
    Prev
    Next
    INDEX
    Explanations

    travel booking services

    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
    ㄓ
    1.12
     UnwrapRef
    1.09
     Symposium
    1.07
     DISTRICT
    1.04
     ORGANIZATION
    1.02
     Organisation
    1.02
     ARTS
    0.99
     Repository
    0.99
     Scalars
    0.98
     WITHIN
    0.97
    POSITIVE LOGITS
    ம்ம
    0.82
    /
    0.82
    .
    0.81
    (
    0.75
    '
    0.74
    com
    0.73
    NBC
    0.73
     MTV
    0.72
    о
    0.72
     nour
    0.70
    Activations Density 0.033%

    No Known Activations