© 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. 10405
    Prev
    Next
    INDEX
    Explanations

    not motivated

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

    The neuron strongly activates on decimal number tokens (numerical values with fractional parts).

    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
    ം
    0.92
    ف
    0.89
    ح
    0.89
    د
    0.85
    я
    0.85
    istanbul
    0.78
    га
    0.77
    س
    0.77
    してる
    0.76
    т
    0.76
    POSITIVE LOGITS
     Mait
    0.69
     mesti
    0.68
    록
    0.67
    ."
    0.67
     खूब
    0.67
    laki
    0.66
     Этот
    0.66
     estatales
    0.66
    별
    0.66
    Mgr
    0.65
    Activations Density 0.001%

    No Known Activations