© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 303
    Prev
    Next
    INDEX
    Explanations

    specific tokens and common punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    !
    0.94
    ↵↵
    0.90
     Point
    0.86
    o
    0.84
    :
    0.84
     stomp
    0.83
    ት
    0.83
     Version
    0.80
    dehyde
    0.80
     Gap
    0.78
    POSITIVE LOGITS
    ের
    1.10
    땃
    1.05
    ﺍ
    1.05
     américains
    1.04
    ים
    1.02
     bialgebras
    1.02
    𝐟
    0.96
    ों
    0.96
    년대
    0.96
    𝐛
    0.96
    Activations Density 0.000%

    No Known Activations