© 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. 12813
    Prev
    Next
    INDEX
    Explanations

    as mentioned

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

    The neuron detects numerical data values—especially floating‐point numbers or large numeric 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
    Figura
    0.76
    น
    0.76
     vezes
    0.75
    nič
    0.73
    นิ
    0.72
    mais
    0.71
    mp
    0.71
    neigh
    0.71
    ydney
    0.70
    쭈
    0.68
    POSITIVE LOGITS
     ribosomes
    0.79
     Sections
    0.78
     sections
    0.77
     methylation
    0.76
     Extracts
    0.73
     Considerable
    0.72
    ною
    0.71
     inputRange
    0.71
     joins
    0.71
     concaten
    0.70
    Activations Density 0.032%

    No Known Activations