© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13982
    Prev
    Next
    INDEX
    Explanations

    'told' or 'said' followed by prepositions

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

    This neuron detects speech‐attribution phrases, i.e. instances of “said” following a speaker name.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ។
    0.75
    イング
    0.69
    それが
    0.64
    importanza
    0.63
     Marsden
    0.63
    ഡ്
    0.62
     normalcy
    0.62
     أنه
    0.62
     nonchal
    0.61
     важно
    0.61
    POSITIVE LOGITS
     told
    0.65
    $
    0.59
    told
    0.58
    ور
    0.54
     of
    0.52
    video
    0.51
     proposé
    0.50
    '
    0.50
    ír
    0.49
    డయ
    0.49
    Activations Density 0.020%

    No Known Activations