© 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. 1422
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens with decimal points, i.e. floating-point measurements.

    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
    <0x9A>
    0.58
    వాన్ని
    0.57
    ‍ह
    0.55
    icksburg
    0.54
     जिलों
    0.54
    ellige
    0.54
    婫
    0.53
    үү
    0.53
    ozyg
    0.53
     रूट्स
    0.53
    POSITIVE LOGITS
    within
    0.52
    Term
    0.51
     পদক্ষেপ
    0.51
    credit
    0.50
    Object
    0.50
     delle
    0.50
    Exist
    0.50
    Log
    0.49
    Boolean
    0.49
    Jab
    0.49
    Activations Density 0.000%

    No Known Activations