© 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. 127806
    Prev
    Next
    INDEX
    Explanations

    technical status and errors

    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
     will
    -1.58
     or
    -1.42
     essere
    -1.37
    しましょう
    -1.33
     your
    -1.23
    錘
    -1.20
    egli
    -1.20
     zwei
    -1.19
    閏
    -1.19
     ложки
    -1.18
    POSITIVE LOGITS
    seem
    1.73
    seems
    1.58
    apparently
    1.48
    Seems
    1.47
    appears
    1.45
     "];
    1.43
     seems
    1.41
     seem
    1.38
     semblent
    1.38
    seemed
    1.33
    Activations Density 0.220%

    No Known Activations