© 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. 90708
    Prev
    Next
    INDEX
    Explanations

    proteasomal degradation pathway

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

    scientific terms related to proteases, proteosomes, or CD3 molecules in biological research.

    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
    ")]
    -1.66
    )");
    -1.61
    }),
    -1.56
     fêtes
    -1.53
    )":
    -1.51
    \"",
    -1.48
    żyć
    -1.47
    𝓜
    -1.42
    ',
    -1.42
    ми
    -1.39
    POSITIVE LOGITS
     i
    1.69
    <i>
    1.68
     نقاط
    1.38
     is
    1.37
    がない
    1.34
     I
    1.33
     наиболее
    1.33
    i
    1.27
     location
    1.24
    Y
    1.24
    Activations Density 0.043%

    No Known Activations