© 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. 58471
    Prev
    Next
    INDEX
    Explanations

    Licensed under

    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
     atve
    -1.08
     tava
    -0.95
     teks
    -0.94
    عود
    -0.93
    riceps
    -0.90
     vieta
    -0.88
     kampus
    -0.88
     restoran
    -0.88
     sade
    -0.88
     fok
    -0.87
    POSITIVE LOGITS
    azer
    0.90
    zards
    0.85
    cení
    0.83
    Abuja
    0.81
     Arty
    0.80
     messengers
    0.78
    nior
    0.78
     spelt
    0.77
     undersø
    0.76
     therewith
    0.76
    Activations Density 0.000%

    No Known Activations