© 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. 56941
    Prev
    Next
    INDEX
    Explanations

    pro se

    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
    ńst
    -0.90
    راحی
    -0.78
     ceny
    -0.76
     Poets
    -0.75
    gebnis
    -0.72
    vignon
    -0.71
     Egan
    -0.69
    支出
    -0.69
     Gers
    -0.69
    voye
    -0.68
    POSITIVE LOGITS
     pror
    3.84
     pro
    3.73
    pro
    2.33
     Pro
    2.06
     про
    2.00
    Pro
    1.95
     proportional
    1.86
    プロ
    1.77
     pr
    1.71
     proportionate
    1.63
    Activations Density 0.025%

    No Known Activations