© 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. 13920
    Prev
    Next
    INDEX
    Explanations

    words starting with "Sec"

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

    This neuron is triggered by tokens beginning with “Sec” that denote section references (e.g. “Sec228,” “sectional,” “Sec212”).

    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
    }
    -2.83
    ↵↵
    -2.52
    rétaire
    -2.39
    .
    -2.27
    </h3>
    -2.22
     touted
    -2.22
     warmen
    -2.19
    Other
    -2.17
     bilden
    -2.11
    ному
    -2.09
    POSITIVE LOGITS
    a
    3.13
    甚至
    2.39
     {\
    2.39
    咴
    2.38
    "];
    2.28
    >
    2.28
    ene
    2.28
    鉿
    2.23
     mentre
    2.20
    
    2.20
    Activations Density 0.010%

    No Known Activations