© 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. 7932
    Prev
    Next
    INDEX
    Explanations

    )

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

    This neuron detects numeric tokens and numeric expressions (e.g. view counts, prices, deadlines, measurements) 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
     A
    0.73
     อ
    0.69
     Α
    0.69
     А
    0.68
    بالإنجليزية
    0.66
     Ρ
    0.64
     Μ
    0.64
     Ι
    0.64
     Ν
    0.62
    ッと
    0.60
    POSITIVE LOGITS
    ↵↵
    0.75
     contraire
    0.54
    ↵↵↵
    0.53
     duquel
    0.52
    🤧
    0.52
                               
    0.52
     fapt
    0.52
     samband
    0.52
    ↵
    0.49
    $$
    0.49
    Activations Density 0.057%

    No Known Activations