© 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. 3406
    Prev
    Next
    INDEX
    Explanations

    0

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

    This neuron activates on precise numeric tokens with 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
    mity
    0.63
     surrog
    0.63
    ુ
    0.62
     elementType
    0.61
    inputFile
    0.61
    bmod
    0.59
     disguised
    0.59
     filtr
    0.59
    ᠠ
    0.59
    ाइब
    0.58
    POSITIVE LOGITS
     fabulous
    0.74
     옆
    0.73
    옆
    0.70
     LON
    0.67
     maravilh
    0.66
    -...
    0.64
     Patti
    0.64
     phenomenal
    0.64
     những
    0.63
     தா
    0.63
    Activations Density 0.000%

    No Known Activations