© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13608
    Prev
    Next
    INDEX
    Explanations

    calculate, estimate, find, solve

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

    The neuron activates on decimal numeric values, spotting floating‐point numbers in the text.

    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
     caval
    0.75
     brav
    0.70
     audacious
    0.68
    -
    0.68
     loved
    0.66
     could
    0.66
     eyeballs
    0.65
    א
    0.64
     afar
    0.63
     au
    0.63
    POSITIVE LOGITS
    栦
    0.75
    ᠩ
    0.73
    çe
    0.70
     दट
    0.70
    栨
    0.70
     specifics
    0.69
    dateTime
    0.69
    具体的
    0.69
    цију
    0.69
    鿁
    0.68
    Activations Density 0.000%

    No Known Activations