© 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. 10-GEMMASCOPE-RES-131K
    7. 7494
    Prev
    Next
    INDEX
    Explanations

    broth extract

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

    This neuron detects references to "broth" in scientific contexts, particularly in laboratory and fermentation settings.

    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
    鸲
    -3.64
    橚
    -3.55
    嫪
    -3.00
    Ꭳ
    -2.91
    鸶
    -2.83
    嗩
    -2.69
     apparaat
    -2.67
    ᯾
    -2.61
     \
    -2.58
    薆
    -2.55
    POSITIVE LOGITS
    '
    2.91
    \
    2.59
    有
    2.36
    然后
    2.14
     If
    2.14
    culada
    2.08
    ".
    2.05
     avid
    2.03
    可以
    2.02
    有著
    2.02
    Activations Density 0.000%

    No Known Activations