© 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. 77839
    Prev
    Next
    INDEX
    Explanations

    date formatting and code initialization

    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
     produttore
    -0.75
    рованию
    -0.73
     prawn
    -0.72
     dasar
    -0.72
    짬
    -0.71
     epide
    -0.70
     gine
    -0.70
     described
    -0.69
     apparently
    -0.69
     Membuat
    -0.69
    POSITIVE LOGITS
     FDR
    0.94
    рти
    0.86
    FDR
    0.81
     сожалению
    0.77
     forState
    0.77
     disc
    0.76
    eev
    0.75
    kona
    0.75
     fal
    0.74
    views
    0.74
    Activations Density 0.008%

    No Known Activations