© 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. 4167
    Prev
    Next
    INDEX
    Explanations

    when the

    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
     І
    2.29
     交換
    2.26
     Artisan
    2.14
    іб
    2.14
    NGTH
    2.11
    🗸
    2.11
     Appointments
    2.09
     Propriet
    2.09
     ②
    2.06
    чатку
    2.05
    POSITIVE LOGITS
    rer
    1.53
    ind
    1.30
     الاطلاع
    1.23
    rical
    1.23
     die
    1.20
    apps
    1.19
    ger
    1.18
     být
    1.15
    ूल
    1.14
    benhav
    1.13
    Activations Density 0.000%

    No Known Activations