© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99826
    Prev
    Next
    INDEX
    Explanations

    SQL stored procedures

    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
    ZIONI
    -0.75
     replaceable
    -0.71
     délais
    -0.70
    dags
    -0.70
     зво
    -0.69
     prezzo
    -0.69
    ᴉ
    -0.68
    ʧ
    -0.68
     réussite
    -0.67
     Outils
    -0.67
    POSITIVE LOGITS
     sp
    1.25
    sp
    1.22
     tbl
    1.18
     dbo
    1.14
    tbl
    1.04
     defaultstate
    0.93
     VW
    0.90
     tb
    0.89
    vw
    0.89
     [
    0.88
    Activations Density 0.041%

    No Known Activations