© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63170
    Prev
    Next
    INDEX
    Explanations

    thread.sleep or return

    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
    quema
    -0.77
     Treasures
    -0.69
     forfeit
    -0.69
     常
    -0.68
    彩色
    -0.66
    fif
    -0.66
     toilette
    -0.65
     ocupa
    -0.64
     encontrar
    -0.64
     føl
    -0.64
    POSITIVE LOGITS
    })}$
    0.78
     Reboot
    0.73
     genom
    0.67
    جميع
    0.65
    '])){
    0.65
    гу
    0.65
     Gaw
    0.65
    룡
    0.65
    Tyler
    0.65
    January
    0.65
    Activations Density 0.041%

    No Known Activations