© 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. 31282
    Prev
    Next
    INDEX
    Explanations

    sleep and mattress

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

    The neuron strongly activates on unusually long tokens, effectively flagging words with many characters.

    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
    buildings
    -0.95
     小型
    -0.80
    drawSprites
    -0.78
    zsh
    -0.78
    bertson
    -0.77
    located
    -0.77
    tainer
    -0.75
    black
    -0.75
     jacket
    -0.74
     lapel
    -0.74
    POSITIVE LOGITS
     sleep
    2.78
     mattress
    2.73
     sleeping
    2.72
    Sleep
    2.50
     slept
    2.45
     Sleep
    2.45
     sleeps
    2.45
    sleeping
    2.36
    Sleeping
    2.33
    sleep
    2.27
    Activations Density 0.057%

    No Known Activations