© 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. 2908
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ริม
    -0.69
    નું
    -0.69
     empiric
    -0.69
     nhận
    -0.68
     proves
    -0.68
     Win
    -0.67
     globals
    -0.67
     Erskine
    -0.67
     propagating
    -0.67
    Init
    -0.67
    POSITIVE LOGITS
    Kun
    0.88
    celebr
    0.82
     gabbana
    0.81
    ECU
    0.80
    Shock
    0.80
     advertiser
    0.79
    Talla
    0.78
    IOC
    0.76
     queima
    0.75
     россий
    0.75
    Activations Density 0.011%

    No Known Activations