© 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. 85547
    Prev
    Next
    INDEX
    Explanations

    magazine descriptions

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

    The neuron is highly sensitive to numerical expressions (years, measurements, dates, and other numeric tokens, including decimals).

    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
     with
    -1.87
     you
    -1.70
    躄
    -1.68
     then
    -1.66
     —
    -1.63
     or
    -1.52
     they
    -1.48
    他の
    -1.39
     albeit
    -1.35
     if
    -1.34
    POSITIVE LOGITS
    
    1.73
     periódico
    1.63
     disques
    1.56
     ſch
    1.48
     balles
    1.48
    啣
    1.47
     mères
    1.47
    举动
    1.46
    asional
    1.41
     verſ
    1.39
    Activations Density 0.134%

    No Known Activations