© 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. 14851
    Prev
    Next
    INDEX
    Explanations

    orchestrating events or sequences

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

    The neuron detects occurrences of the verb “orchestrate” (in any tense or morphological form).

    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
    ſſel
    -2.61
    鲞
    -2.36
    2
    -2.33
    ꒥
    -2.31
    蛲
    -2.28
     fratelli
    -2.27
    ౮
    -2.27
    
    -2.25
    纡
    -2.23
    ቼ
    -2.23
    POSITIVE LOGITS
    x
    3.11
    ↵
    2.73
    U
    2.55
     We
    2.55
    〠
    2.47
     —
    2.09
    衅
    2.05
    
    2.05
    )$
    2.03
    霂
    2.03
    Activations Density 0.007%

    No Known Activations