© 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. 13202
    Prev
    Next
    INDEX
    Explanations

    explaining or relating concepts

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

    The main thing this neuron does is detect floating‐point numbers (numerical tokens with decimal points).

    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
     ກ
    0.83
    0.80
     Beloved
    0.77
     Aurang
    0.76
     pengh
    0.75
    eclipse
    0.74
    though
    0.73
    treatment
    0.72
     perangkat
    0.72
     ৪র্থ
    0.72
    POSITIVE LOGITS
    ვე
    0.73
    ხვევ
    0.73
    çons
    0.66
    ovou
    0.65
    ovac
    0.65
     села
    0.64
    簪
    0.64
    чне
    0.64
    ťou
    0.63
    sterne
    0.63
    Activations Density 0.000%

    No Known Activations