© 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. 59511
    Prev
    Next
    INDEX
    Explanations

    Ram, Nivas, Gadkari, Convention, Garden, Vilas

    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
     затем
    -0.75
    particularly
    -0.74
     darunter
    -0.70
    唷
    -0.69
     hump
    -0.68
    Ран
    -0.68
    ียน
    -0.68
     inic
    -0.68
     instin
    -0.67
     ryt
    -0.67
    POSITIVE LOGITS
    fdb
    0.75
    ixels
    0.75
    襬
    0.73
     首
    0.73
     kötü
    0.72
    ůž
    0.72
     Người
    0.71
     qualifier
    0.70
     poème
    0.70
     receivers
    0.69
    Activations Density 0.013%

    No Known Activations