© 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. 43407
    Prev
    Next
    INDEX
    Explanations

    leasing opportunities

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

    The neuron fires on tokens that contain internal uppercase letters (e.g. CamelCase identifiers or proper-name compounds).

    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
    逦
    -2.89
     dibujado
    -2.56
    ări
    -2.56
     复古
    -2.45
    ではでは
    -2.39
     gustado
    -2.36
    さてさて
    -2.34
     绒
    -2.33
    其妙
    -2.28
    謠
    -2.28
    POSITIVE LOGITS
    ."
    3.83
    '
    3.41
    s
    3.31
     '
    3.11
     "
    3.05
    ,"
    2.81
    "
    2.81
    ra
    2.78
    ")
    2.63
    {
    2.55
    Activations Density 0.002%

    No Known Activations