© 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. 16657
    Prev
    Next
    INDEX
    Explanations

    sounds, visuals, and physical phenomena

    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
    July
    -1.33
     GOtt
    -1.29
    を行い
    -1.28
     ASSIGNMENT
    -1.19
    it
    -1.16
    archical
    -1.16
    一只
    -1.14
     včetně
    -1.13
     augen
    -1.12
     daz
    -1.11
    POSITIVE LOGITS
     or
    1.96
     یا
    1.44
     when
    1.32
    jangan
    1.28
     или
    1.28
     because
    1.27
     salonu
    1.27
    CastException
    1.20
     vagy
    1.20
     and
    1.20
    Activations Density 0.048%

    No Known Activations