© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83989
    Prev
    Next
    INDEX
    Explanations

    definition/example

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

    The neuron is highly sensitive to short, common function words (stopwords) and discourse connectors like “a,” “but,” “rather,” “about,” etc.

    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
    ÜR
    -0.84
     Theses
    -0.82
     eer
    -0.81
     Masses
    -0.81
     giver
    -0.81
     oven
    -0.81
     hoj
    -0.79
    テナンス
    -0.78
     discos
    -0.76
    resie
    -0.75
    POSITIVE LOGITS
    副本
    0.90
     subsidy
    0.90
     placebo
    0.85
    工具类
    0.84
     referral
    0.82
     considerar
    0.81
     hacer
    0.81
     checksum
    0.79
    getExtras
    0.79
     temporary
    0.78
    Activations Density 0.276%

    No Known Activations