© 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. 11073
    Prev
    Next
    INDEX
    Explanations

    environmental conditions and states

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

    words related to environmental conditions or physical stressors like temperature, heat, pressure, and humidity.

    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
    seido
    -1.13
     okolo
    -1.09
    tismo
    -1.02
     школу
    -1.00
     hebdomada
    -1.00
    ENSEN
    -0.98
     tournant
    -0.95
    憷
    -0.94
    mapsto
    -0.91
     leçon
    -0.90
    POSITIVE LOGITS
    ItemView
    1.04
     temperature
    1.02
    lectricité
    0.96
    ICIÓN
    0.93
     Other
    0.92
     Webseiten
    0.91
    Other
    0.89
     Arabian
    0.88
    limsy
    0.88
     diesmal
    0.88
    Activations Density 0.080%

    No Known Activations