© 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. 74852
    Prev
    Next
    INDEX
    Explanations

    Hoover, honeycomb, resorption

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

    scientific or technical terms, especially in chemistry, biology, and materials science.

    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
     There
    -2.81
    驀
    -2.78
     Unfortunately
    -2.77
     Although
    -2.72
     Some
    -2.69
     Usually
    -2.59
     Probably
    -2.53
     Despite
    -2.53
     However
    -2.50
     Perhaps
    -2.48
    POSITIVE LOGITS
    (
    2.55
     dando
    2.41
     –
    2.36
    )
    2.22
    \
    2.20
    cu
    2.19
    1
    2.19
    ть
    2.16
    ar
    2.08
    苤
    2.08
    Activations Density 0.067%

    No Known Activations