© 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. 32771
    Prev
    Next
    INDEX
    Explanations

    official dates and events

    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
     use
    -0.91
     χρήση
    -0.86
    บริการ
    -0.84
    objetos
    -0.84
    cstring
    -0.84
     उपयोग
    -0.83
    Sick
    -0.82
     maturity
    -0.82
    サミ
    -0.82
     Glaubens
    -0.81
    POSITIVE LOGITS
     early
    1.33
     oficialmente
    1.16
     officially
    1.16
     официаль
    1.09
     official
    1.05
    OFFICIAL
    1.02
     sớm
    0.99
     menetapkan
    0.98
     unofficial
    0.97
    早めに
    0.97
    Activations Density 0.086%

    No Known Activations