© 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. 105746
    Prev
    Next
    INDEX
    Explanations

    SQL definition for varchar columns

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

    The neuron flags occurrences of the “maxcdn” token in Bootstrap CDN URLs.

    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
    ⟝
    -2.38
    It
    -2.25
    雰
    -2.22
    巔
    -2.20
    呓
    -2.19
     spécialisé
    -2.14
    Of
    -2.14
     Seventy
    -2.14
    橚
    -2.13
     thirty
    -2.11
    POSITIVE LOGITS
    衪
    2.31
    ↵↵
    2.28
    ist
    1.98
    '
    1.97
    箆
    1.96
    er
    1.93
    typeDefinition
    1.85
     ويمكن
    1.84
    蕺
    1.81
    styleType
    1.80
    Activations Density 0.001%

    No Known Activations