© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66682
    Prev
    Next
    INDEX
    Explanations

    biodiversity and its effects

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

    The neuron activates for the word "biodiversity" and related concepts in scientific or environmental contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron predominantly fires on the term “biodiversity” (and closely related environmental‐science keywords).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ;
    
    -2.94
     или
    -2.89
    涠
    -2.73
    婼
    -2.67
     یا
    -2.42
     atau
    -2.34
    埽
    -2.27
    燠
    -2.23
    佧
    -2.16
    荜
    -2.14
    POSITIVE LOGITS
    鈊
    2.39
    .
    1.99
    …!
    1.98
     prevailing
    1.98
    摃
    1.94
     stojí
    1.91
     Нужно
    1.90
     glaubte
    1.90
    ついで
    1.88
     Them
    1.84
    Activations Density 0.003%

    No Known Activations