© 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. 57160
    Prev
    Next
    INDEX
    Explanations

    course-related topics and context

    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
     Panel
    -0.83
    trout
    -0.74
    intah
    -0.74
     Camaro
    -0.74
    博士
    -0.74
    бия
    -0.73
     труб
    -0.73
    Panel
    -0.73
     Deposit
    -0.72
    GeoNames
    -0.71
    POSITIVE LOGITS
     course
    0.88
    受講
    0.82
    resistance
    0.81
     amarela
    0.79
    course
    0.77
    OPA
    0.77
    Course
    0.77
    ('.')
    0.77
    weeks
    0.75
    cour
    0.74
    Activations Density 0.013%

    No Known Activations