© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128991
    Prev
    Next
    INDEX
    Explanations

    names of Giovanni and Antoine

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

    The neuron activates on personal names (proper nouns referring to individuals), especially Italian given names.

    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
    0
    -3.22
    or
    -3.16
    this
    -3.16
    a
    -3.02
    或者
    -2.91
    \
    -2.89
    Y
    -2.88
    ”
    -2.72
    甚至
    -2.72
    或
    -2.56
    POSITIVE LOGITS
    鳙
    2.67
    Ꮞ
    2.63
    Pgina
    2.61
    鲻
    2.58
    
    2.48
    buatan
    2.45
    哙
    2.44
     From
    2.42
    служба
    2.38
    鲽
    2.38
    Activations Density 0.003%

    No Known Activations