© 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. 89960
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
     pantal
    -0.76
    blems
    -0.76
    一辈子
    -0.75
     Balkon
    -0.75
     approving
    -0.75
    ншот
    -0.75
    consensus
    -0.73
    titanium
    -0.73
    遊んで
    -0.72
    seros
    -0.72
    POSITIVE LOGITS
     respond
    1.31
     opportunity
    1.30
     defend
    1.28
     defence
    1.23
     explain
    1.23
     response
    1.23
     presentation
    1.20
     defense
    1.16
     presenting
    1.15
     explanation
    1.14
    Activations Density 0.020%

    No Known Activations