© 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. 34-GEMMASCOPE-RES-131K
    7. 108192
    Prev
    Next
    INDEX
    Explanations

    locations and names

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

    The neuron is sensitive to numeric tokens and measurement expressions (digits, years, quantities, and associated units).

    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
    grass
    -0.82
    trero
    -0.81
    ého
    -0.78
    secuted
    -0.77
     Wochenende
    -0.72
    Πηγ
    -0.71
     表示
    -0.71
    geoning
    -0.70
     śmier
    -0.70
     juega
    -0.70
    POSITIVE LOGITS
     Organized
    1.09
    Organized
    0.99
    organized
    0.99
     organizado
    0.97
     pine
    0.93
     organized
    0.93
     Organize
    0.90
     Kef
    0.85
    SetFont
    0.85
     чере
    0.84
    Activations Density 0.017%

    No Known Activations