© 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. 4457
    Prev
    Next
    INDEX
    Explanations

    time, access, accuracy, statement

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

    The neuron is highly activated by numeric tokens, especially floating‐point numbers.

    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
     affections
    0.78
     windings
    0.77
    았
    0.77
     operatives
    0.74
    ковка
    0.73
    ो
    0.73
     всеми
    0.73
    ಾ
    0.72
     gills
    0.71
     upgrades
    0.71
    POSITIVE LOGITS
    Jenis
    0.89
    ^{*}}\
    0.86
    ostiene
    0.84
    mathrm
    0.82
    ęcie
    0.80
    énération
    0.80
    pués
    0.79
    California
    0.79
     concetto
    0.79
     Fungsi
    0.77
    Activations Density 0.001%

    No Known Activations