© 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. 85123
    Prev
    Next
    INDEX
    Explanations

    linen and flax

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

    This neuron specifically activates on mentions of “linen,” effectively detecting occurrences of that textile term.

    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
    ’;
    -2.98
    ⃢
    -2.73
    谂
    -2.61
    ⡪
    -2.48
    於是
    -2.44
    ጺ
    -2.36
    !’
    -2.33
    ൅
    -2.27
    厖
    -2.25
     údaj
    -2.19
    POSITIVE LOGITS
    ra
    2.73
    that
    2.50
     Если
    2.47
    >
    2.42
    釭
    2.41
    媖
    2.30
    hasilkan
    2.23
    ?'
    2.19
    ção
    2.17
    ization
    2.09
    Activations Density 0.002%

    No Known Activations