© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38356
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

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

    The neuron fires on occurrences of the Latin letter “ṣ” (s with a dot below), as used in transliterated Semitic names.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    [
    -3.41
     have
    -2.86
    *
    -2.64
    ją
    -2.55
    ;
    -2.48
    だが
    -2.47
    on
    -2.47
    ...
    -2.44
    there
    -2.36
    ありますが
    -2.31
    POSITIVE LOGITS
     edifici
    2.83
     trattato
    2.83
    糴
    2.83
    鉏
    2.73
     amazingly
    2.64
     utilizzare
    2.61
     giusti
    2.61
    咘
    2.58
     delightfully
    2.58
     unbelievably
    2.58
    Activations Density 0.003%

    No Known Activations