© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78826
    Prev
    Next
    INDEX
    Explanations

    geyser, minerals, stalactites, hydrothermal

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

    geological and natural formation terms, especially those related to caves, minerals, and volcanic features.

    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
    AGCT
    -0.88
     tiredness
    -0.77
     sweetness
    -0.73
     freuen
    -0.71
     profitability
    -0.71
    荊
    -0.71
     integrations
    -0.69
     parity
    -0.68
    rane
    -0.68
    beza
    -0.66
    POSITIVE LOGITS
     Yellowstone
    1.38
     hydrothermal
    0.99
    NPS
    0.98
    옐
    0.91
     violen
    0.90
    YELLOW
    0.87
     fumar
    0.86
    Yellow
    0.84
     geothermal
    0.84
    boiling
    0.84
    Activations Density 0.011%

    No Known Activations