© 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. 116628
    Prev
    Next
    INDEX
    Explanations

    foreign language words and English license/copyright

    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
     Amber
    -0.70
    BarItem
    -0.68
     капсу
    -0.68
    ioren
    -0.66
     anew
    -0.66
    MIB
    -0.66
     TWO
    -0.66
    复杂
    -0.65
    TID
    -0.65
     amber
    -0.63
    POSITIVE LOGITS
     Kier
    0.73
    letra
    0.72
     Viewer
    0.70
    tête
    0.69
     enkel
    0.69
     التف
    0.68
     гля
    0.68
     heer
    0.68
     Personalized
    0.68
    letters
    0.67
    Activations Density 0.059%

    No Known Activations