© 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. 19362
    Prev
    Next
    INDEX
    Explanations

    position followed by code syntax

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

    The neuron flags numeric literals (especially floating‐point numbers) in the code.

    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
     obiet
    -2.73
     sicura
    -2.73
     eccellente
    -2.73
     perfetta
    -2.70
     humeur
    -2.69
    窳
    -2.67
     opinie
    -2.59
     leggera
    -2.56
     jeste
    -2.52
     bluza
    -2.52
    POSITIVE LOGITS
    -
    3.98
    '
    3.72
     \
    3.42
    ated
    3.02
    ↵
    2.95
    1
    2.83
    0
    2.73
    4
    2.69
    5
    2.67
    3
    2.66
    Activations Density 0.004%

    No Known Activations