© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1932
    Prev
    Next
    INDEX
    Explanations

    named entity or description

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

    The neuron fires on occurrences of “named” (especially capitalized “Named”) in code identifiers or imports.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Deals
    -0.90
    UNG
    -0.90
    Frédéric
    -0.84
    Trails
    -0.82
    deals
    -0.81
    jerne
    -0.81
    Streamer
    -0.81
    dragons
    -0.79
    Rhin
    -0.79
     prefeitura
    -0.78
    POSITIVE LOGITS
    named
    1.07
    tuple
    1.02
     Named
    0.94
    arg
    0.91
    Named
    0.90
    Пі
    0.87
    uses
    0.84
    Uses
    0.83
     named
    0.83
    IsTrue
    0.81
    Activations Density 0.020%

    No Known Activations