© 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. 10539
    Prev
    Next
    INDEX
    Explanations

    legal propagation internal explicit deep

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

    The neuron strongly activates on isolated, infrequent or specialized tokens—e.g. proper names, technical terms, numbers, and other rare words.

    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
    lif
    0.82
    standen
    0.80
    send
    0.78
    sound
    0.77
    lige
    0.77
    app
    0.77
    d
    0.77
    l
    0.76
    我的
    0.76
    sat
    0.73
    POSITIVE LOGITS
     Procurement
    0.95
    ꯦ
    0.90
     обязанности
    0.84
     Digest
    0.84
     Iterate
    0.84
     Collaborate
    0.83
    ToExp
    0.82
     REV
    0.82
    marshalO
    0.82
     PROC
    0.81
    Activations Density 0.000%

    No Known Activations