© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40879
    Prev
    Next
    INDEX
    Explanations

    eutrophication, round robin, spontaneous ergic

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

    The neuron is primarily picking out multi‐syllabic subword fragments—especially affixes and stems in compound or technical terms.

    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
    へ行
    -1.95
    ↵
    -1.78
     impossibile
    -1.77
    惩
    -1.68
    阶级
    -1.66
     discuss
    -1.63
    ッシング
    -1.63
    se
    -1.63
     venture
    -1.62
    éraire
    -1.60
    POSITIVE LOGITS
     klara
    2.06
    镦
    1.97
     bebek
    1.83
    很棒
    1.81
     Mathf
    1.81
     arbeta
    1.80
    \
    1.80
     abiye
    1.77
     dekoratif
    1.71
    kese
    1.71
    Activations Density 0.037%

    No Known Activations