© 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. 12513
    Prev
    Next
    INDEX
    Explanations

    multi-language titles

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

    The neuron predominantly fires on tokens that are decimal‐formatted numbers (i.e. multi-digit values 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
     \"
    0.70
     """"
    0.70
     `#
    0.69
     "#
    0.69
     Templates
    0.69
     Feuerwehr
    0.66
     '"
    0.66
     “
    0.65
     \#
    0.65
     Arrange
    0.64
    POSITIVE LOGITS
    или
    0.75
    женной
    0.73
    もしくは
    0.69
    как
    0.67
    非常に
    0.66
    probabilities
    0.66
    品種
    0.66
    ิล
    0.65
    ោង
    0.64
    または
    0.64
    Activations Density 0.001%

    No Known Activations