© 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. 14555
    Prev
    Next
    INDEX
    Explanations

    liquid crystal, squares, molecular

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

    technical or scientific terms, particularly references to crystals, molecules, and mathematical or physical concepts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on multi‐word technical compound terms, for example adjective + noun collocations like “least squares,” “liquid crystal,” “dental amalgams,” or “high molecular.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    雠
    -1.59
    </strong>
    -1.59
    (/^
    -1.58
     we
    -1.57
    𓋼
    -1.56
    lores
    -1.55
     proceeding
    -1.53
     lifts
    -1.51
     one
    -1.50
    ;";
    -1.48
    POSITIVE LOGITS
    </h5>
    1.95
     También
    1.81
     също
    1.73
     indirec
    1.70
     Además
    1.69
     Después
    1.63
    を作る
    1.59
    <bos>
    1.55
    有点
    1.50
     Estas
    1.46
    Activations Density 0.038%

    No Known Activations