© 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. 22-GEMMASCOPE-RES-131K
    7. 128466
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric values representing nuclear‐spin quantum numbers (e.g. “I = 3/2”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    EC, DP, Q, Daily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     даже
    -1.36
    Tác
    -1.18
    Sự
    -1.18
     уже
    -1.17
     who
    -1.13
    Many
    -1.09
     even
    -1.09
    Đặc
    -1.08
    Even
    -1.07
    зопас
    -1.07
    POSITIVE LOGITS
     głównie
    1.13
    ween
    1.11
     partiellement
    1.05
     relinquish
    0.99
    そこは
    0.97
     vägen
    0.97
     halve
    0.97
    囹
    0.96
    ogados
    0.96
    绊
    0.95
    Activations Density 0.000%

    No Known Activations