© 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. 84127
    Prev
    Next
    INDEX
    Explanations

    require('express'), require('fs'), require('path')

    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
     různých
    -1.63
     verschillende
    -1.58
     valamint
    -1.55
    裢
    -1.48
     mobilya
    -1.48
     estándares
    -1.44
     skon
    -1.40
     editados
    -1.39
     потім
    -1.39
     lã
    -1.38
    POSITIVE LOGITS
     because
    1.73
    3
    1.67
    1
    1.41
     may
    1.37
     Although
    1.33
     хотя
    1.32
     came
    1.30
    6
    1.27
     is
    1.26
     بری
    1.26
    Activations Density 0.026%

    No Known Activations