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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32248
    Prev
    Next
    INDEX
    Explanations

    polling

    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
     실행
    -0.72
     Trilogy
    -0.71
     Preven
    -0.71
     Resolver
    -0.71
    bakken
    -0.70
     taxonomic
    -0.68
    铿
    -0.68
    Prun
    -0.68
    ♪♪
    -0.67
    Rese
    -0.67
    POSITIVE LOGITS
     poll
    3.14
     polling
    3.05
    poll
    2.97
    Poll
    2.77
     Poll
    2.67
    POLL
    2.48
     polls
    2.38
     POLL
    2.31
    Polling
    2.23
    polling
    2.19
    Activations Density 0.050%

    No Known Activations