© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90898
    Prev
    Next
    INDEX
    Explanations

    voice opinion or concern

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

    The neuron specifically fires on occurrences of the verb “voice” (especially “voiced”) indicating that someone is expressing an opinion or feeling.

    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
     That
    -2.59
     ONLY
    -2.56
    媜
    -2.42
     While
    -2.36
     Even
    -2.33
     Despite
    -2.25
    ?
    -2.20
     Like
    -2.16
     Making
    -2.11
     Regardless
    -2.11
    POSITIVE LOGITS
    没有
    2.42
    
    2.38
     trám
    2.30
    我只
    2.27
    嫑
    2.23
    an
    2.22
    鰊
    2.20
    我一直
    2.19
    泂
    2.14
    ໊
    2.09
    Activations Density 0.003%

    No Known Activations