© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25222
    Prev
    Next
    INDEX
    Explanations

    class definitions and methods

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

    The neuron activates primarily on numeric literals (digits, hex values, and other numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    -0.94
    の概要
    -0.91
     your
    -0.91
     cou
    -0.87
     petro
    -0.86
    mical
    -0.85
    hadores
    -0.84
     другому
    -0.84
    dia
    -0.84
     you
    -0.83
    POSITIVE LOGITS
     pochette
    0.96
     Dumnezeu
    0.94
     funko
    0.90
     horloge
    0.90
     plie
    0.88
     avena
    0.88
     autonomie
    0.88
     masques
    0.88
     citroen
    0.86
     victimes
    0.86
    Activations Density 0.016%

    No Known Activations