© 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. 72256
    Prev
    Next
    INDEX
    Explanations

    making decisions

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

    The neuron primarily activates on the word “decisions” (i.e. occurrences of “decision”/“decisions”).

    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
    Negative Logits
    y
    -3.03
     You
    -2.92
    )
    -2.77
     potret
    -2.56
     Ihre
    -2.55
    ⌑
    -2.45
    ⃙
    -2.34
    ionali
    -2.34
    ("
    -2.31
    sivos
    -2.28
    POSITIVE LOGITS
    .
    2.89
    肏
    2.50
    辚
    2.48
    ・・・。
    2.36
    抔
    2.30
    んや
    2.30
    谞
    2.30
     был
    2.28
    颼
    2.22
    
    2.20
    Activations Density 0.020%

    No Known Activations