© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11935
    Prev
    Next
    INDEX
    Explanations

    Sent: followed by date/time

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

    The neuron fires on metadata and structural tokens in header or boilerplate blocks—things like line numbers, timestamps, “Sent,” “specific,” “AS,” and other comment/license‐header markers.

    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
     outro
    -0.68
     واي
    -0.67
     halves
    -0.67
     produ
    -0.66
    Crack
    -0.65
     Builder
    -0.65
    hnung
    -0.65
     знак
    -0.65
     выбора
    -0.65
     horses
    -0.65
    POSITIVE LOGITS
     défis
    0.76
     Trink
    0.75
     krie
    0.71
    ENTLY
    0.67
     Inlet
    0.66
    NOUNC
    0.64
    eltas
    0.63
    Vinc
    0.63
    setOpen
    0.63
     pergi
    0.62
    Activations Density 0.060%

    No Known Activations