© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5991
    Prev
    Next
    INDEX
    Explanations

    numbers with units like %, pounds, or in time formats

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

    The neuron fires on numeric tokens (digits and numbers, including multi‐digit and decimal sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    decimal numbers, particularly those between 0 and 10 with one or two decimal places.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    u
    1.00
    in
    0.80
     Dem
    0.80
    ar
    0.76
     flanges
    0.75
    เคร
    0.74
     Du
    0.72
    esque
    0.72
     Delt
    0.72
    ০
    0.72
    POSITIVE LOGITS
    ﺖ
    0.82
     Abgerufen
    0.81
    лите
    0.79
    Embedding
    0.79
    llen
    0.78
    ất
    0.77
    Imaging
    0.77
    ﺔ
    0.77
    Assignments
    0.76
    Naming
    0.76
    Activations Density 0.577%

    No Known Activations