© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14430
    Prev
    Next
    INDEX
    Explanations

    activity or process

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

    The neuron strongly activates on numeric or data‐style tokens (years, measurements, statistics, citations), effectively spotting numbers and metadata markers in the text.

    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
    ható
    0.84
    اری
    0.80
    ι
    0.79
    ಧಾನ
    0.78
     Value
    0.76
    编辑器
    0.73
    细胞
    0.73
    صورت
    0.73
    ުޅ
    0.72
     Literary
    0.71
    POSITIVE LOGITS
    ဤ
    0.85
    рку
    0.71
     ожи
    0.70
    <h3>
    0.68
    нина
    0.68
     conclure
    0.67
    ogyakarta
    0.67
    ;
    0.67
    これを
    0.66
     slapping
    0.66
    Activations Density 0.000%

    No Known Activations