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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12311
    Prev
    Next
    INDEX
    Explanations

    governmental health and related organizations

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

    organizations and official government entities mentioned in formal documents or reports.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     设计
    -1.36
    ervant
    -1.30
     kulak
    -1.27
     schuhe
    -1.27
     فقط
    -1.25
    ﻄ
    -1.24
     vanta
    -1.23
     ilustrasi
    -1.22
     ได้
    -1.21
    食べる
    -1.20
    POSITIVE LOGITS
     their
    1.85
     in
    1.65
     government
    1.36
     cucharadas
    1.34
     at
    1.33
     all
    1.30
     within
    1.23
     inspiradoras
    1.23
     decorativas
    1.20
     of
    1.16
    Activations Density 0.035%

    No Known Activations