© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73341
    Prev
    Next
    INDEX
    Explanations

    described, reported facts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     their
    -1.27
     соответственно
    -1.04
     they
    -1.04
    Hopefully
    -0.95
    x
    -0.94
    そうです
    -0.91
     hivyo
    -0.91
    撿
    -0.90
     (*.
    -0.88
    Travelling
    -0.87
    POSITIVE LOGITS
     although
    1.25
    dapat
    1.10
     even
    1.09
    fvar
    0.94
    uerto
    0.94
    жин
    0.94
    criminate
    0.93
    érias
    0.92
    PHPExcel
    0.90
     reivindic
    0.90
    Activations Density 0.053%

    No Known Activations