© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64269
    Prev
    Next
    INDEX
    Explanations

    simulation and simulators

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    嘿嘿
    -2.41
     $<
    -2.25
     we
    -2.13
     notre
    -2.09
     мы
    -2.03
     tinkering
    -2.03
     $>
    -1.98
     conocemos
    -1.95
     jejich
    -1.95
    >
    -1.89
    POSITIVE LOGITS
    y
    2.73
    m
    2.38
    x
    2.34
    {
    2.11
     –
    2.05
    ).
    2.02
    et
    2.02
    （※
    1.99
    u
    1.96
     ๆ
    1.95
    Activations Density 0.015%

    No Known Activations