© 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. 34-GEMMASCOPE-RES-131K
    7. 3503
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
    Negative Logits
    selbe
    -0.98
     startling
    -0.94
     tandis
    -0.93
    Ꮫ
    -0.92
     interactiva
    -0.91
     ถ
    -0.91
    lasts
    -0.90
     last
    -0.90
    шкой
    -0.89
     cinquième
    -0.88
    POSITIVE LOGITS
     as
    1.11
     manure
    1.02
     one
    1.00
     indicates
    1.00
     aeronau
    0.98
    ندما
    0.96
     ONLY
    0.93
     before
    0.90
     brings
    0.87
     admittance
    0.87
    Activations Density 0.032%

    No Known Activations