© 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. 1022
    Prev
    Next
    INDEX
    Explanations

    educational contexts and reports

    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
     youth
    -0.88
     teens
    -0.84
     pupils
    -0.83
     teenagers
    -0.81
    Exercises
    -0.80
     userEmail
    -0.80
    imágenes
    -0.77
    kine
    -0.77
     Figuren
    -0.77
     adolescentes
    -0.77
    POSITIVE LOGITS
     Harcourt
    0.87
     rotations
    0.83
    旋转
    0.82
     mathematicians
    0.81
     ovi
    0.81
    λί
    0.80
     Sponsorship
    0.79
     centers
    0.78
     pouches
    0.77
    ACCEPTED
    0.77
    Activations Density 0.017%

    No Known Activations