© 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. 35777
    Prev
    Next
    INDEX
    Explanations

    governing boards and authorities

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

    The neuron detects “by”-phrases that name the agent in passive or administrative constructions (e.g. “administered by…”).

    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
     to
    -1.37
    未必
    -1.30
     Besøkt
    -1.19
    diteur
    -1.12
     Deixe
    -1.11
     界
    -1.07
    Източници
    -1.05
     curated
    -1.03
    atalyst
    -1.03
    ++$
    -1.02
    POSITIVE LOGITS
    decisions
    1.34
     bestuur
    1.32
     colchón
    1.29
     governing
    1.28
     control
    1.27
     exercices
    1.21
     chaleco
    1.20
    下一步
    1.19
     authority
    1.18
     cheveux
    1.18
    Activations Density 0.047%

    No Known Activations