© 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. 14937
    Prev
    Next
    INDEX
    Explanations

    code delimiters and libraries

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

    The neuron fires on numeric tokens—especially floating‐point values and other numbers—i.e. it detects 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
    ة
    0.57
    ри
    0.49
    =
    0.48
    га
    0.48
    е
    0.47
    '
    0.46
    אם
    0.45
    ա
    0.44
    /
    0.44
    2
    0.44
    POSITIVE LOGITS
     grandes
    0.39
     foro
    0.39
     magasins
    0.38
     poaching
    0.38
     moeil
    0.38
     impulsar
    0.38
     grands
    0.38
    ிகளில்
    0.38
     boutiques
    0.37
     Vestone
    0.37
    Activations Density 0.031%

    No Known Activations