© 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. 19678
    Prev
    Next
    INDEX
    Explanations

    purge and bulimia

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

    terms related to purging, whether in medical contexts (eating disorders), mechanical systems, or political contexts.

    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
    </h3>
    -3.27
     mohou
    -3.11
    訁
    -2.52
     kterou
    -2.42
    </strong>
    -2.39
    ...")
    -2.33
     můžete
    -2.30
     mogą
    -2.30
     pomá
    -2.22
    </em>
    -2.20
    POSITIVE LOGITS
     或
    2.47
    ,
    2.33
    <bos>
    2.25
     purge
    2.22
     veren
    1.99
     یا
    1.98
     varsa
    1.89
    外的
    1.84
    </b>
    1.84
    ני
    1.84
    Activations Density 0.002%

    No Known Activations