© 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. 65900
    Prev
    Next
    INDEX
    Explanations

    various occasions and uses

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

    The neuron detects general‐scope determiners and quantifiers (e.g. “your,” “various,” “any,” “all”) that broadly address or categorize items.

    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
     洗濯
    -0.82
    itteet
    -0.80
    jenkins
    -0.78
    miche
    -0.77
     時計
    -0.76
    ┚
    -0.75
    licit
    -0.75
     mister
    -0.73
    inske
    -0.72
    wär
    -0.70
    POSITIVE LOGITS
     occasions
    1.38
     DIY
    1.21
     scenes
    1.16
     places
    1.13
     uses
    1.09
     scene
    1.07
    Scene
    1.06
     steder
    1.05
     activities
    1.02
     occasion
    1.00
    Activations Density 0.019%

    No Known Activations