© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12941
    Prev
    Next
    INDEX
    Explanations

    programming and code snippets

    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_13_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
    ^+,
    1.17
    -【
    1.09
     prelimin
    1.08
    氟
    1.05
     guidelines
    1.02
     Guidelines
    1.01
     rules
    1.01
    歲
    1.00
    VERTISING
    1.00
     qualitatively
    0.99
    POSITIVE LOGITS
     sua
    2.97
     seu
    2.90
     suas
    2.88
     his
    2.56
     jego
    2.55
     его
    2.54
     njegova
    2.39
     njegove
    2.39
    his
    2.38
     उसकी
    2.38
    Activations Density 0.483%

    No Known Activations