© 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. 62705
    Prev
    Next
    INDEX
    Explanations

    codes and commands

    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
     because
    -0.88
    miques
    -0.80
     apoyar
    -0.79
     participó
    -0.78
    閑
    -0.77
     terminado
    -0.74
    していました
    -0.71
    thail
    -0.71
    örü
    -0.71
     lanzó
    -0.71
    POSITIVE LOGITS
     gracious
    0.90
    lja
    0.78
    迎接
    0.77
    ède
    0.77
    selo
    0.77
     domicili
    0.76
    enumi
    0.75
     bild
    0.75
    比特派
    0.75
    prozess
    0.74
    Activations Density 0.036%

    No Known Activations