© 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. 10-GEMMASCOPE-RES-131K
    7. 22610
    Prev
    Next
    INDEX
    Explanations

    one at a time

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    }$
    -2.31
    {
    -2.09
     ‘
    -2.09
     and
    -2.03
    It
    -2.03
    6
    -1.91
    ?’
    -1.90
    9
    -1.89
    5
    -1.88
    2
    -1.78
    POSITIVE LOGITS
     stringBy
    2.13
    甡
    1.98
    艄
    1.93
    荭
    1.92
     så
    1.88
     proposons
    1.84
    剮
    1.84
     circonst
    1.83
    的で
    1.80
    杙
    1.80
    Activations Density 0.003%

    No Known Activations