© 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. 66922
    Prev
    Next
    INDEX
    Explanations

    case, therefore, or example

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

    This neuron detects sentence-level discourse or transition adverbials (e.g. “In any case,” “Moreover,” “For example,” “Therefore,” etc.) typically followed by a comma.

    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
    鼕
    -1.56
    ⟐
    -1.48
     jossa
    -1.48
    襞
    -1.42
     suuri
    -1.41
     عندما
    -1.41
     kuid
    -1.41
     Which
    -1.40
     вовсе
    -1.38
     mahd
    -1.38
    POSITIVE LOGITS
    m
    2.06
    to
    1.75
     .
    1.73
    </h3>
    1.68
    \
    1.67
     ,‬
    1.59
    originally
    1.45
     to
    1.44
    y
    1.44
     we
    1.41
    Activations Density 0.003%

    No Known Activations