© 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. 72759
    Prev
    Next
    INDEX
    Explanations

    microwaves, X-rays, clouds, opioids, optics

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

    scientific terminology related to waves, radiation, and electromagnetic phenomena.

    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
    ܆
    -1.92
    </em>
    -1.82
    ♪♪
    -1.77
    들이
    -1.75
     nostre
    -1.74
    　　*
    -1.66
    Перевод
    -1.66
     kèo
    -1.66
     rosse
    -1.65
    纔
    -1.65
    POSITIVE LOGITS
    \
    1.77
     was
    1.69
    </h1>
    1.66
    Skocz
    1.66
     &
    1.59
     satisfecho
    1.56
     
    1.55
    ’
    1.53
    utusan
    1.52
    seye
    1.49
    Activations Density 0.374%

    No Known Activations