© 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. 16581
    Prev
    Next
    INDEX
    Explanations

    athletic United Davis Neural Efficacy

    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
    為に
    -1.20
    interpr
    -1.20
     duża
    -1.09
    ようです
    -1.08
     goederen
    -1.05
     sıcak
    -1.05
     moż
    -1.04
    gigabyte
    -1.04
     utilizz
    -1.02
     geplant
    -1.02
    POSITIVE LOGITS
     Meny
    1.19
    Neutron
    1.11
     diagnos
    1.11
     monit
    1.09
     aspi
    1.09
     Poh
    1.08
     poros
    1.08
    //*
    1.06
    Migrations
    1.06
     instru
    1.06
    Activations Density 0.000%

    No Known Activations