© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70461
    Prev
    Next
    INDEX
    Explanations

    creosote Gall

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

    scientific or technical terms ending with "ote" (like "nanote", "creosote", "amastigote").

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

    This neuron strongly activates on tokens containing the substring “ote,” i.e. words ending in or including “ote” (e.g. epimastigote, creosote, heterozygote, etc.).

    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
    ’
    -3.41
    2
    -3.13
    p
    -2.98
    /
    -2.92
    3
    -2.88
    9
    -2.86
    6
    -2.83
    d
    -2.75
    1
    -2.69
    the
    -2.67
    POSITIVE LOGITS
    菹
    2.92
     anún
    2.83
    ieR
    2.69
    闞
    2.52
     azienda
    2.50
    煳
    2.48
    齡
    2.47
    yyv
    2.34
    烔
    2.34
    我现在
    2.33
    Activations Density 0.027%

    No Known Activations