© 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. 10-GEMMASCOPE-RES-131K
    7. 59331
    Prev
    Next
    INDEX
    Explanations

    astronauts, Argonauts, jurors

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

    The neuron is attuned to occurrences of the word “astronaut.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ญี่ป
    -2.64
    lossians
    -2.45
    咝
    -2.41
    sudadera
    -2.36
    螓
    -2.34
    苼
    -2.31
     Dengan
    -2.28
    ть
    -2.23
    és
    -2.23
    TryDecode
    -2.20
    POSITIVE LOGITS
    𓋼
    2.58
     respective
    2.55
    I
    2.33
    D
    2.30
    👨
    2.28
     supposed
    2.17
    C
    2.17
    ↵↵
    2.17
    $
    2.16
    In
    2.14
    Activations Density 0.002%

    No Known Activations