© 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. 15786
    Prev
    Next
    INDEX
    Explanations

    say "code punctuation"

    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
    ស
    0.60
    综合
    0.54
    ท้าย
    0.51
    呼
    0.50
    ১১
    0.49
    ज़
    0.49
     разно
    0.49
    zeugt
    0.48
    કના
    0.48
    뭅
    0.48
    POSITIVE LOGITS
     wear
    0.98
    ’:
    0.96
    ’;
    0.93
    wear
    0.93
    ’?
    0.89
     Wear
    0.89
    ’,
    0.87
    ’),
    0.85
    ,’
    0.85
    ’)
    0.84
    Activations Density 0.016%

    No Known Activations