© 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. 14766
    Prev
    Next
    INDEX
    Explanations

    governed by, field of

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

    This neuron activates on words that appear in formal terms-and-conditions or eligibility/legal‐disclaimer text (e.g. “open,” “legal,” “residents,” “only,” “governed,” “by,” etc.).

    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
     lixo
    -1.11
     months
    -1.11
     acidente
    -1.08
     acabamento
    -1.07
     equilíbrio
    -1.06
     perigo
    -1.06
     detalhe
    -1.05
     miatt
    -1.05
     imóvel
    -1.05
     treino
    -1.02
    POSITIVE LOGITS
     if
    1.23
    Despite
    1.11
     local
    1.04
     powinna
    1.02
     Despite
    1.02
     in
    1.02
     berusia
    1.01
     perplexing
    1.01
     rozwią
    0.99
     undeniably
    0.99
    Activations Density 0.003%

    No Known Activations