© 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. 10-GEMMASCOPE-RES-131K
    7. 101579
    Prev
    Next
    INDEX
    Explanations

    deforestation and reforestation

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

    environmental terms related to forest destruction and conservation, like "deforestation," "forest loss," and "reforestation."

    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_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
    When
    -2.64
    This
    -2.58
    
    -2.30
    Throughout
    -2.20
     и
    -2.19
    During
    -2.17
    และ
    -2.14
    out
    -2.13
    Honestly
    -2.08
    Despite
    -2.05
    POSITIVE LOGITS
    ↵
    2.97
     để
    2.45
    for
    2.39
     mußte
    2.17
    ്ട
    2.09
    i
    2.06
     were
    2.03
    鱘
    2.02
    например
    1.98
    采用了
    1.97
    Activations Density 0.003%

    No Known Activations