© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117145
    Prev
    Next
    INDEX
    Explanations

    pure, impure, purify

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

    HTML/CSS related terms, particularly related to the "pure" CSS framework.

    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_34/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
    rophes
    -0.83
     starvation
    -0.78
    sser
    -0.78
     نا
    -0.77
     бетон
    -0.76
    ̳
    -0.74
    ografi
    -0.73
    Question
    -0.73
     neu
    -0.73
    teren
    -0.72
    POSITIVE LOGITS
     impure
    0.93
     Nada
    0.77
    付き合い
    0.77
     såsom
    0.76
     havi
    0.76
    ~-
    0.75
    nbr
    0.75
     raso
    0.75
    כלי
    0.75
    AMD
    0.74
    Activations Density 0.015%

    No Known Activations