© 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. 13936
    Prev
    Next
    INDEX
    Explanations

    addition symbol

    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
    迺
    0.52
    䅐
    0.51
     plen
    0.47
    newcommand
    0.46
    izoen
    0.45
     mower
    0.45
    চন
    0.44
    cemic
    0.43
     সাক্ষাৎকার
    0.43
    ップ
    0.42
    POSITIVE LOGITS
     +
    4.53
     $+
    4.16
    +
    4.09
     (+
    4.03
     $+$
    3.77
    ,+
    3.77
     +.
    3.72
     +,
    3.69
     $+\
    3.69
    $+
    3.69
    Activations Density 0.144%

    No Known Activations