© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73877
    Prev
    Next
    INDEX
    Explanations

    body parts and organs

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

    This neuron identifies foods that might be considered unusual, strange, or organ meats (like tripe, liver, brains, placenta, brisket, and belly).

    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
    敷地
    -1.45
    ではまた
    -1.43
     sólida
    -1.40
    抬手
    -1.39
    実際の
    -1.39
    ﻞ
    -1.35
    秋の
    -1.34
    它们的
    -1.31
    最新の
    -1.31
    こういった
    -1.31
    POSITIVE LOGITS
    на
    1.57
     */
    1.48
     unſ
    1.44
     of
    1.44
    harapkan
    1.42
     by
    1.40
    l
    1.38
    坶
    1.38
    皛
    1.38
     simplesmente
    1.38
    Activations Density 0.025%

    No Known Activations