© 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. 10416
    Prev
    Next
    INDEX
    Explanations

    command options or parameters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    พ์
    2.50
    十柒章
    2.50
    schild
    2.47
    捌章
    2.45
    秶
    2.38
    ទ្
    2.34
    十捌章
    2.31
     vasena
    2.31
    regate
    2.31
     imassa
    2.31
    POSITIVE LOGITS
    ০০
    2.67
    ġ
    1.88
     Sel
    1.74
     τά
    1.73
    िता
    1.72
    ட
    1.72
    an
    1.71
     G
    1.70
    ወቅ
    1.68
     Rosenthal
    1.67
    Activations Density 0.000%

    No Known Activations