© 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. 103522
    Prev
    Next
    INDEX
    Explanations

    nocturnal sleep

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

    The neuron activates for the word "nocturnal" and sometimes the word "Lyons" in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    拊
    -2.27
    gucig
    -2.25
    鱨
    -2.20
    很赞
    -2.19
    塍
    -2.17
    ᷆
    -2.16
    E
    -2.14
    思议
    -2.14
    葑
    -2.14
    횃
    -2.09
    POSITIVE LOGITS
     That
    2.97
     Даже
    2.73
     Even
    2.64
     vorigen
    2.52
     Then
    2.52
     Not
    2.48
     Hinblick
    2.42
     Zeitraum
    2.30
     For
    2.27
    AutoresizingMask
    2.22
    Activations Density 0.009%

    No Known Activations