© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 16214
    Prev
    Next
    INDEX
    Explanations

    key/GPT

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

    This neuron strongly activates on the final substantive token (the last content word or number) right before a segment’s end or punctuation.

    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
     צ
    0.80
    ל
    0.77
     vann
    0.70
    STOCK
    0.70
     impact
    0.69
    lunch
    0.69
    Ձ
    0.67
     ש
    0.66
    Бы
    0.66
    िमी
    0.66
    POSITIVE LOGITS
     Adelaide
    0.84
    örü
    0.83
    ítě
    0.83
     그랬
    0.82
     उसका
    0.79
    ără
    0.77
     эффектив
    0.76
    ставить
    0.76
     Jeżeli
    0.76
     Cedric
    0.76
    Activations Density 0.001%

    No Known Activations