© 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. 10-GEMMASCOPE-RES-131K
    7. 71598
    Prev
    Next
    INDEX
    Explanations

    event location and timing

    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_10/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
     they
    -1.67
    ográficas
    -1.65
     Сайт
    -1.64
     getNombre
    -1.61
    matism
    -1.59
    晤
    -1.56
     is
    -1.56
    ного
    -1.55
    orice
    -1.55
     ofrecerte
    -1.54
    POSITIVE LOGITS
    ஂ
    1.74
     on
    1.47
     doit
    1.47
    衚
    1.42
    天赋
    1.42
     dagar
    1.41
    (
    1.41
     répondit
    1.38
     politik
    1.38
     werd
    1.38
    Activations Density 0.015%

    No Known Activations