© 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. 127933
    Prev
    Next
    INDEX
    Explanations

    East Germany

    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
     balkon
    -1.42
    颔
    -1.36
     flotte
    -1.34
     karton
    -1.28
     torba
    -1.26
     kalender
    -1.24
     kompak
    -1.20
     dekol
    -1.19
     katastro
    -1.19
     kamera
    -1.19
    POSITIVE LOGITS
     only
    1.37
     others
    1.35
     both
    1.32
     even
    1.31
     asked
    1.23
     not
    1.21
     that
    1.20
     for
    1.18
     how
    1.18
     our
    1.16
    Activations Density 0.000%

    No Known Activations