© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63478
    Prev
    Next
    INDEX
    Explanations

    calls on people

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

    The neuron fires on words that express appeals or calls to action—verbs like “urge,” “call,” “plead,” 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_34/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
    貶
    -1.15
     some
    -1.08
     السياسة
    -1.06
    ﺖ
    -1.04
     meisten
    -1.03
    ágot
    -0.99
     diferite
    -0.96
    多数
    -0.96
    inkas
    -0.96
    peka
    -0.95
    POSITIVE LOGITS
     everyone
    1.70
     all
    1.52
     parents
    1.29
    大家
    1.21
    所有
    1.15
    everyone
    1.13
     young
    1.06
     anyone
    1.05
     employers
    1.02
     institutions
    1.00
    Activations Density 0.020%

    No Known Activations