© 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. 34-GEMMASCOPE-RES-131K
    7. 3625
    Prev
    Next
    INDEX
    Explanations

    average metrics

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    average
    -1.50
     average
    -1.46
    averaged
    -1.41
     averaged
    -1.25
     soportes
    -1.22
    Average
    -1.21
     AVERAGE
    -1.18
    縢
    -1.13
     haupts
    -1.13
    平均
    -1.12
    POSITIVE LOGITS
     over
    1.45
     of
    1.39
     unrelenting
    1.20
     debilitating
    1.13
     Joe
    1.09
     annual
    1.07
     out
    1.06
     for
    1.03
     increase
    1.02
    Joe
    1.02
    Activations Density 0.014%

    No Known Activations