© 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. 41-GEMMASCOPE-2-RES-65K
    7. 13927
    Prev
    Next
    INDEX
    Explanations

    i

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     greater
    1.18
    greater
    1.07
    大于
    0.96
     Greater
    0.94
    GreaterThan
    0.94
     <=
    0.91
     >=
    0.91
     lessor
    0.90
     less
    0.90
    Greater
    0.89
    POSITIVE LOGITS
     Футбол
    0.60
    中央
    0.56
    別
    0.55
    InnoDB
    0.54
    SIE
    0.52
    並
    0.52
     हाता
    0.51
    恂
    0.51
    reality
    0.51
    옵
    0.51
    Activations Density 0.000%

    No Known Activations