© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 86915
    Prev
    Next
    INDEX
    Explanations

    $\textrm{GF}$, code, math symbols

    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
     malta
    -0.77
     coriander
    -0.73
     Office
    -0.69
     Leech
    -0.68
    니까
    -0.68
    lightning
    -0.67
    zoeken
    -0.66
     ALIVE
    -0.66
     مايو
    -0.66
     SHOP
    -0.66
    POSITIVE LOGITS
     وی
    0.82
     frecuentes
    0.69
     barbecue
    0.69
     berlaku
    0.69
     unex
    0.68
     Laur
    0.68
     dương
    0.68
     souls
    0.66
     Bib
    0.66
     Descripción
    0.66
    Activations Density 0.111%

    No Known Activations