© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86471
    Prev
    Next
    INDEX
    Explanations

    wave propagation, environmental fate, systemic mediators

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

    scientific and technical content related to mathematical models, simulations, and systems analysis.

    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
     herbes
    -1.51
    理石
    -1.39
    嘢
    -1.30
    nait
    -1.23
    ówka
    -1.23
     spil
    -1.22
    mping
    -1.21
    哋
    -1.21
    最後に
    -1.20
    ciens
    -1.20
    POSITIVE LOGITS
     you
    1.38
     our
    1.28
     and
    1.19
     through
    1.14
    érfi
    1.13
     various
    1.12
     your
    1.11
     would
    1.09
     Ayrıca
    1.09
     also
    1.08
    Activations Density 0.296%

    No Known Activations