© 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. 103684
    Prev
    Next
    INDEX
    Explanations

    fatty acid, silicic acid, infra-red

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

    scientific and technical terms in academic or professional texts.

    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
    ってみました
    -1.19
    imeter
    -1.16
     особенно
    -1.15
     necesaria
    -1.15
    aways
    -1.14
    tometer
    -1.14
    act
    -1.10
    truct
    -1.08
     otras
    -1.07
     it
    -1.06
    POSITIVE LOGITS
     your
    1.20
    ଼
    1.11
     сегодняш
    1.09
     that
    1.09
    }}^{\
    1.08
    ADELPHIA
    1.06
    attore
    1.05
    Conclusie
    1.05
    iblichen
    1.02
    titanic
    1.02
    Activations Density 0.881%

    No Known Activations