© 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. 45634
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     erneut
    -1.55
    Controllo
    -1.45
     نیز
    -1.43
     Meski
    -1.25
    枇
    -1.24
    Soon
    -1.21
     лишь
    -1.20
     ebenfalls
    -1.18
     également
    -1.17
     станет
    -1.16
    POSITIVE LOGITS
     kind
    2.31
     [
    2.08
     somebody
    1.84
     sort
    1.74
     actually
    1.73
     maybe
    1.70
     probably
    1.66
     everybody
    1.65
     basically
    1.56
     gonna
    1.55
    Activations Density 0.024%

    No Known Activations