© 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. 78293
    Prev
    Next
    INDEX
    Explanations

    Thanksgiving, Sagittari, dates

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

    The neuron detects references to constellations or stellar designations (e.g. Monoceros, X Sagittarii, Capricorn).

    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
     Witcher
    -0.80
    Boxing
    -0.73
     cucumber
    -0.73
    undy
    -0.72
    cucumber
    -0.72
    люсы
    -0.72
    rored
    -0.72
    nuestro
    -0.71
     ябло
    -0.71
    кта
    -0.71
    POSITIVE LOGITS
     Thanksgiving
    1.45
    Thanksgiving
    1.20
     Sag
    1.20
     Sagittarius
    1.07
    Sag
    1.00
     optimism
    0.95
     Nov
    0.92
     optimistic
    0.91
     archers
    0.90
     centa
    0.88
    Activations Density 0.017%

    No Known Activations