© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4532
    Prev
    Next
    INDEX
    Explanations

    print() calls

    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_24_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
    ام
    1.01
    おお
    0.93
    생
    0.92
    gehend
    0.89
    나
    0.89
    Та
    0.88
    у
    0.88
    Га
    0.86
     Τα
    0.85
    يل
    0.84
    POSITIVE LOGITS
     Palt
    0.91
    ('%
    0.89
    ('{
    0.86
    ("\
    0.85
    ('-
    0.83
     labrador
    0.80
    ('|
    0.80
    ('#
    0.78
     tortilla
    0.76
     lysed
    0.76
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.