© 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. 32598
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     may
    -0.94
     some
    -0.92
    oxin
    -0.89
    Quan
    -0.86
     there
    -0.86
     perhaps
    -0.86
     just
    -0.85
     escritor
    -0.84
     many
    -0.84
    esimo
    -0.81
    POSITIVE LOGITS
     rendono
    0.82
    Martes
    0.81
     faptul
    0.81
     NOTHING
    0.81
    줄
    0.79
    ２
    0.77
    cooldown
    0.77
    摻
    0.77
     gdyby
    0.77
    ému
    0.77
    Activations Density 0.002%

    No Known Activations