© 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. 93433
    Prev
    Next
    INDEX
    Explanations

    calculus integration and trigonometric substitution

    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
     season
    -0.70
    Emir
    -0.69
    結成
    -0.68
     müş
    -0.67
    iertamente
    -0.67
    incere
    -0.66
    はずです
    -0.65
    elev
    -0.65
     idle
    -0.64
     extracurricular
    -0.64
    POSITIVE LOGITS
     integration
    3.91
     Integration
    3.58
    Integration
    3.42
    integration
    3.39
     integrate
    3.20
     integrand
    3.11
     integrating
    3.02
    integrate
    2.98
     integrations
    2.81
     integrates
    2.75
    Activations Density 0.091%

    No Known Activations