© 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. 16564
    Prev
    Next
    INDEX
    Explanations

    not certified

    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
     любых
    -0.96
     wszel
    -0.93
    いかない
    -0.90
    Smith
    -0.89
     katalog
    -0.88
    UNTAS
    -0.88
     would
    -0.87
    Mam
    -0.87
     should
    -0.87
    しが
    -0.86
    POSITIVE LOGITS
     atleast
    1.09
     also
    1.09
     there
    1.02
     også
    1.01
     almeno
    0.98
    至少
    0.96
     cuidad
    0.96
    strual
    0.94
     gewähr
    0.94
     arī
    0.94
    Activations Density 0.062%

    No Known Activations