© 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. 4583
    Prev
    Next
    INDEX
    Explanations

    list items with parentheses or commas

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

    This neuron detects numeric tokens representing floating-point numbers (i.e., numbers containing a decimal point).

    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
     решение
    0.64
    МО
    0.61
    nilai
    0.60
     программу
    0.59
     ї
    0.58
    НА
    0.58
    ৷
    0.57
    נו
    0.56
    РА
    0.56
    direccion
    0.55
    POSITIVE LOGITS
     ఇతర
    0.68
     Friedrich
    0.65
     Lakh
    0.64
     G
    0.64
     bastion
    0.64
     autres
    0.61
     other
    0.60
     Ross
    0.60
     anderen
    0.60
     Shah
    0.60
    Activations Density 0.318%

    No Known Activations