© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32348
    Prev
    Next
    INDEX
    Explanations

    org

    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
     what
    -0.83
     something
    -0.81
     there
    -0.78
    -+
    -0.76
    cedar
    -0.73
     tahun
    -0.72
    ages
    -0.71
     or
    -0.71
    زيل
    -0.71
     if
    -0.70
    POSITIVE LOGITS
    tider
    0.87
    chter
    0.84
    Vä
    0.83
    Essen
    0.82
     Auditing
    0.81
    fällig
    0.81
    Apre
    0.81
    燈
    0.80
    不仅
    0.80
    Kä
    0.79
    Activations Density 0.001%

    No Known Activations