© 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. 57007
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers then round

    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
    Not in Any Lists

    No Comments

    Negative Logits
    entie
    -0.77
    ⌫
    -0.74
    Seminar
    -0.69
    隻
    -0.68
     Kode
    -0.68
    ielt
    -0.68
     clon
    -0.68
    Kode
    -0.67
    ELEN
    -0.67
    рый
    -0.66
    POSITIVE LOGITS
     round
    5.38
     rounds
    5.34
    Round
    4.41
     Round
    4.31
    round
    4.22
     Rounds
    3.97
    rounds
    3.84
    Rounds
    3.75
     ROUND
    3.72
    ROUND
    3.69
    Activations Density 0.055%

    No Known Activations