© 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. 22-GEMMASCOPE-RES-131K
    7. 84280
    Prev
    Next
    INDEX
    Explanations

    assistance arriving for someone

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

    The neuron fires on language that explicitly requests or summons aid (e.g. “help,” “call,” “police”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phrases describing requests or calls for assistance or emergency response.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    situations where assistance is sought or provided, especially summoning or receiving emergency response, rescue, or help from authorities or services.

    oai_token-act-pair · gpt-5Triggered 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
     reinigen
    -1.09
    хи
    -1.03
     každý
    -0.98
     Chaque
    -0.96
     individuelles
    -0.95
    ステル
    -0.95
     ۱۶
    -0.95
     ۱۳
    -0.95
    甙
    -0.93
    ﻷ
    -0.93
    POSITIVE LOGITS
     other
    1.34
     help
    1.25
     quickly
    1.24
     while
    1.23
     nearby
    1.21
     assistance
    1.16
     from
    1.16
     people
    1.15
     quick
    1.11
     schnell
    1.07
    Activations Density 0.016%

    No Known Activations