© 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. 128963
    Prev
    Next
    INDEX
    Explanations

    bis or GTK or vena cava

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

    This neuron detects occurrences of the chemical‐nomenclature prefix “bis” in compound names.

    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
     «
    -2.66
     («
    -2.56
     jiné
    -2.30
    灕
    -2.28
    UGHTER
    -2.28
    霂
    -2.27
     of
    -2.20
    
    -2.17
     пары
    -2.14
    譟
    -2.11
    POSITIVE LOGITS
     to
    2.42
    h
    2.34
    ﮨ
    2.28
    O
    2.27
     Your
    2.17
    狃
    2.14
    闼
    2.13
    雖
    2.09
    al
    2.08
     successivamente
    2.08
    Activations Density 0.002%

    No Known Activations