© 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. 86393
    Prev
    Next
    INDEX
    Explanations

    admitted to

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

    The neuron activates on occurrences of the verb “admitted,” i.e. phrases where someone confesses or acknowledges something.

    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
    身影
    -2.70
    してくれた
    -2.58
     nehmen
    -2.58
     he
    -2.56
    神器
    -2.55
     arbeiten
    -2.38
     suchen
    -2.38
    嵛
    -2.30
     také
    -2.30
    
    -2.27
    POSITIVE LOGITS
    ↵
    2.88
    鉺
    2.86
     マグ
    2.73
    袮
    2.73
    
    2.72
    䉴
    2.70
    㐂
    2.69
    腘
    2.67
    
    2.64
     Instead
    2.63
    Activations Density 0.008%

    No Known Activations