© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31233
    Prev
    Next
    INDEX
    Explanations

    numbers and versions

    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
     civiles
    -0.85
    дости
    -0.82
    lords
    -0.82
    vde
    -0.81
    parker
    -0.77
     média
    -0.77
     acide
    -0.77
    quakes
    -0.76
     démon
    -0.74
     poética
    -0.74
    POSITIVE LOGITS
    relse
    0.81
    웰
    0.75
     vettoriale
    0.74
     Apprentices
    0.73
     piecewise
    0.71
     Mumford
    0.71
     прош
    0.71
    Phosp
    0.70
     arrivo
    0.70
     erzählen
    0.70
    Activations Density 0.003%

    No Known Activations