© 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. 12709
    Prev
    Next
    INDEX
    Explanations

    August after year

    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
    Not in Any Lists

    No Comments

    Negative Logits
     analys
    1.20
     потенциа
    1.15
     кабинет
    1.10
     읽
    1.10
    읽
    1.10
     matematik
    1.08
    Kitty
    1.08
    )-\
    1.07
    DY
    1.07
     リ
    1.07
    POSITIVE LOGITS
     timely
    1.05
     dedicated
    0.97
     lawfully
    0.96
     appropriate
    0.96
     mounted
    0.95
     genuinely
    0.92
     Mounted
    0.92
     clothed
    0.91
     honestly
    0.91
    ẽ
    0.90
    Activations Density 0.003%

    No Known Activations