© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124715
    Prev
    Next
    INDEX
    Explanations

    professions and roles

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

    The neuron flags terms naming people’s roles or professions (e.g. comedian, poet, attorney, photographer).

    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
     particular
    -1.26
     being
    -1.20
     extremely
    -1.18
    だという
    -1.14
     Բ
    -1.13
     pregi
    -1.12
     первых
    -1.12
     referred
    -1.10
     referenced
    -1.09
    这个人
    -1.09
    POSITIVE LOGITS
     for
    1.50
    Ⓚ
    1.28
    撰文
    1.21
    　　《
    1.09
     liburan
    1.07
     with
    1.06
     כבר
    1.05
    梦见
    1.05
     vérit
    1.05
     besar
    1.05
    Activations Density 1.114%

    No Known Activations