© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9349
    Prev
    Next
    INDEX
    Explanations

    designed to be

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to rare or content-heavy tokens—especially numerals, proper names, and other low-frequency words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ri
    0.99
    ,
    0.99
    mi
    0.86
    rt
    0.83
    -
    0.82
    an
    0.76
    la
    0.75
    k
    0.75
    se
    0.73
    ع
    0.73
    POSITIVE LOGITS
    ία
    0.88
     pubblico
    0.82
    预防
    0.80
     Seç
    0.79
    रोग
    0.77
     hoş
    0.75
    厨房
    0.75
    韜
    0.75
    स्थल
    0.73
    进一步
    0.72
    Activations Density 0.000%

    No Known Activations