© 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. 84790
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
     first
    -1.09
     primeira
    -0.96
     primera
    -0.90
     or
    -0.87
    inkai
    -0.85
     primeras
    -0.84
     erste
    -0.84
     become
    -0.83
     primeros
    -0.83
     خارجية
    -0.81
    POSITIVE LOGITS
    [
    1.20
     [
    0.88
     SimpleName
    0.87
    뭄
    0.86
    ınız
    0.85
    ɠ
    0.85
    ceğiniz
    0.85
     Typed
    0.84
    '][
    0.84
     Muchas
    0.82
    Activations Density 0.018%

    No Known Activations