© 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. 22-GEMMASCOPE-RES-131K
    7. 70766
    Prev
    Next
    INDEX
    Explanations

    specific topics and details

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

    This neuron fires strongly on the first substantive word of a sentence or new paragraph, marking sentence or paragraph beginnings.

    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
     außerdem
    -1.23
     hingegen
    -1.05
    物語
    -1.02
    影像
    -1.01
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -0.99
    However
    -0.94
    ietf
    -0.93
     situatie
    -0.92
     moreover
    -0.91
    ↵↵↵↵↵↵↵↵
    -0.90
    POSITIVE LOGITS
     how
    1.95
     specifically
    1.67
     topics
    1.44
    Specifically
    1.42
     particularly
    1.34
    specifically
    1.34
    cómo
    1.32
     Specifically
    1.30
     khususnya
    1.28
     topic
    1.27
    Activations Density 0.118%

    No Known Activations