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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109093
    Prev
    Next
    INDEX
    Explanations

    Green functions and correlation functions

    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
    polynomial
    -0.79
    Calculation
    -0.77
    LMS
    -0.72
     QUI
    -0.72
     Calculation
    -0.70
     XM
    -0.70
     ایرانی
    -0.69
    UP
    -0.69
    ciem
    -0.69
    UID
    -0.68
    POSITIVE LOGITS
     propag
    1.85
     Green
    1.51
    propag
    1.35
    Green
    1.27
     Propag
    1.16
     resol
    1.14
    resol
    1.14
     Greens
    1.12
     green
    1.07
    green
    1.07
    Activations Density 0.022%

    No Known Activations