© 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. 34-GEMMASCOPE-RES-131K
    4. 82793
    Prev
    Next
    INDEX
    Explanations

    Illustration

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

    The neuron activates on words containing the root “illu” (e.g. illusory, illusion, illustration, illustrator).

    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
     écrite
    -0.96
    Handled
    -0.88
    isesta
    -0.86
     denen
    -0.86
     mouthpiece
    -0.85
     виро
    -0.85
     姜
    -0.82
     ascribe
    -0.82
     electors
    -0.79
     ExecuteAsync
    -0.79
    POSITIVE LOGITS
    ations
    1.09
    AGRAM
    1.04
    strator
    1.02
    stration
    0.99
     ilust
    0.99
    ustra
    0.93
    ประกอบ
    0.90
    trate
    0.90
     ilustração
    0.87
     complications
    0.87
    Activations Density 0.016%

    No Known Activations