© 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. 70151
    Prev
    Next
    INDEX
    Explanations

    Hermann Warm, Arturo Martini, cataracts, epidemiology

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

    names, scientific terms, and medical conditions at the beginning of text segments.

    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
     prochaine
    -3.00
    揶
    -2.77
     blames
    -2.59
    轶
    -2.59
     nosso
    -2.53
     beverages
    -2.52
    錬
    -2.52
     eradicated
    -2.44
    躋
    -2.39
    会の
    -2.36
    POSITIVE LOGITS
    觏
    2.91
    之意
    2.80
    赜
    2.67
    .
    2.64
    ——”
    2.45
     renewed
    2.41
     zorro
    2.39
    除此之外
    2.38
     baden
    2.34
    1
    2.33
    Activations Density 0.015%

    No Known Activations