© 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. 1682
    Prev
    Next
    INDEX
    Explanations

    numbers and word counts

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

    The neuron fires on numeric tokens, especially multi‐digit quantities or 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
    ᅪ
    0.50
     เนื่องจาก
    0.46
    Date
    0.45
    ﻼ
    0.44
    EndGlobalSection
    0.43
    Acad
    0.42
    Campus
    0.42
    ᅯ
    0.42
    Vertex
    0.41
    FontFace
    0.41
    POSITIVE LOGITS
     જેટ
    0.56
     percent
    0.55
     dollari
    0.51
     dollars
    0.50
     cumulative
    0.49
     (!)
    0.47
    范围内
    0.47
     acres
    0.47
    percent
    0.46
    dollars
    0.46
    Activations Density 0.206%

    No Known Activations