© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103781
    Prev
    Next
    INDEX
    Explanations

    Kichwa

    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
    Confusion
    -0.74
    riebene
    -0.71
     ujung
    -0.71
     ír
    -0.71
    acyjnych
    -0.69
     habari
    -0.69
     旅
    -0.69
    confusion
    -0.68
    >.</
    -0.68
    Cursed
    -0.68
    POSITIVE LOGITS
    комо
    0.75
    Hence
    0.75
     hence
    0.75
    本格
    0.73
    ophosph
    0.71
    ത്
    0.71
     nuoc
    0.71
     キ
    0.71
    znám
    0.71
    viamo
    0.70
    Activations Density 0.031%

    No Known Activations