© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2921
    Prev
    Next
    INDEX
    Explanations

    lists of capitalized words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Kog
    1.74
    igenous
    1.70
     Ethnic
    1.66
    ocommit
    1.65
     andolan
    1.64
    KLC
    1.63
    kezi
    1.61
    ajati
    1.60
    듈
    1.58
     jml
    1.58
    POSITIVE LOGITS
     via
    1.15
     tov
    1.04
     through
    0.96
    cylinder
    0.92
     pert
    0.92
    through
    0.91
    thru
    0.87
     thru
    0.86
     weiterhin
    0.86
     بسر
    0.84
    Activations Density 0.015%

    No Known Activations