© 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. 64974
    Prev
    Next
    INDEX
    Explanations

    shortcut icon, PUBLIC software

    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
     DOB
    -0.72
     рай
    -0.71
     Pineapple
    -0.68
    line
    -0.68
    pdo
    -0.67
    select
    -0.66
     mast
    -0.66
    master
    -0.64
     Line
    -0.64
    kol
    -0.63
    POSITIVE LOGITS
     bohater
    0.73
     служи
    0.73
    щаются
    0.70
    askin
    0.68
     Hail
    0.68
    chengla
    0.67
    MIM
    0.67
    Lav
    0.66
    heath
    0.66
    カット
    0.64
    Activations Density 0.047%

    No Known Activations