© 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. 10140
    Prev
    Next
    INDEX
    Explanations

    lactic acid biosynthesis

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

    the prefix "Lac" in various words, such as "Laconia," "LacZ," and "lactam."

    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
     ส์
    -3.09
     biografia
    -3.08
     唯美
    -3.06
    Архівовано
    -3.05
    〜〜
    -2.86
    硖
    -2.86
    犸
    -2.77
    囌
    -2.70
     faca
    -2.69
     anún
    -2.67
    POSITIVE LOGITS
    ’
    4.53
    "
    4.47
    (
    4.16
    \
    3.95
    am
    3.08
    ↵
    2.98
    at
    2.83
    }
    2.80
    ми
    2.63
     «
    2.63
    Activations Density 0.005%

    No Known Activations