© 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. 3955
    Prev
    Next
    INDEX
    Explanations

    Sequential Processing

    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
    ل
    2.59
    وم
    2.34
    تب
    2.22
    au
    2.15
    op
    2.10
    nu
    2.09
    aur
    2.05
    etition
    2.05
    ندگی
    2.03
    론
    2.00
    POSITIVE LOGITS
    doubt
    2.81
    iries
    2.70
    stylesheet
    2.69
    sent
    2.69
     कमलेश
    2.68
    httpRequest
    2.63
     impress
    2.63
     Periodic
    2.60
    subscription
    2.57
    лені
    2.56
    Activations Density 0.010%

    No Known Activations