© 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. 71835
    Prev
    Next
    INDEX
    Explanations

    opportunity and, Effect of, Search form

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

    The neuron flags formal template or legal-style policy language—e.g. tokens from code/test case headers (like “tmpl”) and compliance/disclaimer terms in equal-opportunity statements.

    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
     évé
    -1.54
     türkiye
    -1.52
    AxisSize
    -1.27
     palab
    -1.27
     MÉ
    -1.23
     anadolu
    -1.23
     Deportes
    -1.20
     NDEBUG
    -1.20
     Дет
    -1.20
    离开了
    -1.19
    POSITIVE LOGITS
     Sortiment
    1.27
     as
    1.20
     instead
    1.19
     also
    1.18
    six
    1.15
     allgemeinen
    1.14
     schicken
    1.13
    three
    1.12
    two
    1.10
     Deshalb
    1.10
    Activations Density 0.000%

    No Known Activations