© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10363
    Prev
    Next
    INDEX
    Explanations

    travel by driving

    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_7_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
    ی
    3.08
    न
    2.93
    arote
    2.74
    sels
    2.56
    offel
    2.49
    ာ
    2.48
    ៊ី
    2.47
    ransport
    2.47
    ipt
    2.44
    serrat
    2.41
    POSITIVE LOGITS
    தலாக
    2.95
    ತ್ಮ
    2.75
    thest
    2.39
    昧
    2.38
    vine
    2.31
    ქვს
    2.31
    訶
    2.28
    menuid
    2.28
    ges
    2.27
     majeure
    2.23
    Activations Density 0.027%

    No Known Activations