© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70413
    Prev
    Next
    INDEX
    Explanations

    professions and titles

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

    The neuron detects mentions of people’s names and titles (i.e. proper-name entities and professional honorifics).

    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
     terima
    -1.20
     beż
    -1.19
    夏季
    -1.19
     torneo
    -1.16
    ῾
    -1.14
    الغ
    -1.12
    uating
    -1.11
     versión
    -1.09
    弟子
    -1.09
    fikation
    -1.08
    POSITIVE LOGITS
    You
    1.49
     you
    1.42
     says
    1.41
    Your
    1.38
     devemos
    1.26
     recommends
    1.23
     say
    1.15
    How
    1.13
     www
    1.13
    Any
    1.13
    Activations Density 0.049%

    No Known Activations