© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40797
    Prev
    Next
    INDEX
    Explanations

    multi-language names and words

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

    This neuron selectively activates on proper names (especially place and personal names) from African or Swahili contexts.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    تصویر
    -1.84
     remé
    -1.84
     упаковке
    -1.82
     です
    -1.79
    蕷
    -1.75
     végétal
    -1.73
     déchir
    -1.70
    ویژگی
    -1.70
     régal
    -1.66
     flé
    -1.65
    POSITIVE LOGITS
     of
    2.06
     vorigen
    1.84
     they
    1.77
    但
    1.72
     commento
    1.68
     we
    1.63
     Anſ
    1.63
    这
    1.63
     GOtt
    1.63
     другую
    1.63
    Activations Density 0.003%

    No Known Activations