© 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. 13806
    Prev
    Next
    INDEX
    Explanations

    blank placeholder

    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
     forcibly
    0.59
     колон
    0.58
     stdout
    0.56
    DROP
    0.54
    😂😂
    0.54
     well
    0.53
     ngOnInit
    0.53
    ！！！
    0.52
     !!!!
    0.51
    搞笑
    0.51
    POSITIVE LOGITS
    __
    0.97
     __
    0.95
    __,
    0.76
    __:
    0.74
    __'
    0.74
    __.
    0.73
     ___
    0.70
    __|
    0.66
    __[
    0.66
     '__
    0.66
    Activations Density 0.000%

    No Known Activations