© 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. 13513
    Prev
    Next
    INDEX
    Explanations

    origin, population, infection, handling specific content

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

    The neuron fires on numeric tokens—i.e. it detects numbers (including decimals, measurements, coordinates, statistics) 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
    snow
    0.86
    ic
    0.82
    accord
    0.78
    état
    0.76
    }>
    0.74
    charm
    0.73
    sunset
    0.73
    سال
    0.72
    如同
    0.72
    ⇐
    0.71
    POSITIVE LOGITS
     eventualmente
    0.89
     matar
    0.84
     allegations
    0.84
     terminations
    0.84
     ответственность
    0.82
     mostrado
    0.79
     tiene
    0.76
     sentencia
    0.76
     correto
    0.76
     administrativo
    0.76
    Activations Density 0.000%

    No Known Activations