© 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. 34-GEMMASCOPE-RES-131K
    7. 117006
    Prev
    Next
    INDEX
    Explanations

    Arctic permafrost research

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

    text related to northern or arctic regions, particularly content about geographical locations, climate, or environmental conditions.

    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_34/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
     Mysore
    -0.77
     frutto
    -0.76
    lüğ
    -0.72
     Kauf
    -0.71
    uarga
    -0.71
     tygod
    -0.71
     multe
    -0.70
    tds
    -0.69
    ujący
    -0.69
    pedes
    -0.68
    POSITIVE LOGITS
    thaw
    1.07
     Alaska
    1.06
    Alaska
    1.03
     Arctic
    1.03
     Yukon
    0.98
     thaw
    0.92
    Ice
    0.91
     caribou
    0.91
     Inu
    0.90
    Arctic
    0.86
    Activations Density 0.029%

    No Known Activations