© 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. 9754
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

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

    The neuron spikes on tokens that are raw numeric strings (especially long sequences of digits and decimal 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
    /">
    0.80
    gericht
    0.80
    cx
    0.79
    infodisc
    0.77
    aria
    0.77
    ü
    0.77
    won
    0.76
    kbd
    0.76
    ता
    0.75
    chrift
    0.75
    POSITIVE LOGITS
     onde
    0.89
     *(
    0.83
     s
    0.81
     A
    0.81
     אבל
    0.80
     Alters
    0.79
     l
    0.78
     Ο
    0.77
     ডিভিশ
    0.77
     ἔ
    0.77
    Activations Density 0.020%

    No Known Activations