© 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. 2256
    Prev
    Next
    INDEX
    Explanations

    in the context

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

    The neuron fires on numeric tokens containing decimal points (floating‐point 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
    ਾਂ
    0.76
     日本製
    0.73
     ฉาก
    0.70
     της
    0.69
    在该
    0.68
    ﺎ
    0.67
    eture
    0.66
     读取
    0.66
    sthe
    0.65
     '#'
    0.65
    POSITIVE LOGITS
     vicinity
    0.90
     aftermath
    0.78
     midst
    0.75
     Nähe
    0.73
    mediately
    0.72
     meantime
    0.69
     absence
    0.68
     earliest
    0.67
     соответствии
    0.66
     months
    0.65
    Activations Density 0.071%

    No Known Activations