© 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. 118676
    Prev
    Next
    INDEX
    Explanations

    copyright and license text

    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
     privacidade
    -0.91
    Ikr
    -0.87
    ▆
    -0.84
    mleri
    -0.83
    ὐ
    -0.78
     背包
    -0.77
     Bankers
    -0.77
     Sermons
    -0.77
    რ
    -0.76
    beautiful
    -0.76
    POSITIVE LOGITS
    WB
    0.73
     IBS
    0.71
    bj
    0.70
     HBV
    0.69
     considering
    0.69
     WB
    0.69
    IB
    0.68
    AB
    0.68
     UNIX
    0.67
     Henrique
    0.66
    Activations Density 0.150%

    No Known Activations