© 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. 60526
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    Bat
    -0.85
    Derived
    -0.72
    ஆ
    -0.71
    telser
    -0.70
    Ін
    -0.70
    umented
    -0.70
    representation
    -0.69
    leneck
    -0.69
    amment
    -0.69
    press
    -0.69
    POSITIVE LOGITS
     pir
    0.70
     cans
    0.66
     sigh
    0.66
     remo
    0.65
    居酒屋
    0.64
     frontal
    0.63
     motility
    0.63
    tiglie
    0.63
     esti
    0.63
    ค่ะ
    0.61
    Activations Density 0.085%

    No Known Activations