© 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. 47213
    Prev
    Next
    INDEX
    Explanations

    main menu

    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
     maïs
    -1.23
    rophoresis
    -1.20
    КУ
    -1.19
    wasn
    -1.19
    Ữ
    -1.15
     específica
    -1.14
     flesta
    -1.13
    もあります
    -1.12
     aktiviteter
    -1.12
     scă
    -1.11
    POSITIVE LOGITS
     and
    1.16
    Even
    1.09
    T
    1.05
    来週
    1.05
    増加
    1.03
    At
    1.03
    To
    1.02
    F
    1.02
    V
    1.01
    L
    1.00
    Activations Density 0.000%

    No Known Activations