© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38923
    Prev
    Next
    INDEX
    Explanations

    special characters and code definitions

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

    The neuron fires on the phrase pattern “no … effect on,” essentially spotting negated-effect statements (e.g. “no concomitant effect on”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     during
    -1.28
    Марина
    -0.92
    During
    -0.90
    たび
    -0.87
    அ
    -0.86
    解锁
    -0.85
    Добавлено
    -0.85
    gräns
    -0.84
     on
    -0.84
     BEFORE
    -0.84
    POSITIVE LOGITS
    ication
    0.95
     jaka
    0.93
     czemu
    0.93
     лікар
    0.92
     фильма
    0.92
    tifications
    0.92
     різних
    0.91
    sias
    0.91
     dlaczego
    0.90
     mú
    0.90
    Activations Density 0.065%

    No Known Activations