© 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. 11815
    Prev
    Next
    INDEX
    Explanations

    the `module` or `class`

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

    The neuron activates on numeric tokens (especially floating‐point or multi‐digit numbers).

    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
     엄청
    0.92
    iktar
    0.89
    spending
    0.88
    Loksatta
    0.88
    譏
    0.85
     спорта
    0.84
    <unused1864>
    0.84
    abhavo
    0.83
     создание
    0.83
    
    0.82
    POSITIVE LOGITS
     corresponding
    1.07
     first
    0.97
     standard
    0.96
     correspond
    0.96
     second
    0.95
     V
    0.94
     S
    0.94
     non
    0.93
     X
    0.89
     J
    0.89
    Activations Density 0.302%

    No Known Activations