© 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. 10-GEMMASCOPE-RES-131K
    7. 84357
    Prev
    Next
    INDEX
    Explanations

    turning on and off devices

    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_10/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
    s
    -2.36
    0
    -2.25
    (?)
    -1.90
    sandalia
    -1.85
    跄
    -1.75
     with
    -1.60
     ketika
    -1.59
    ter
    -1.57
     (?)
    -1.55
    ParallelGroup
    -1.55
    POSITIVE LOGITS
    嫵
    1.87
    噥
    1.82
     marvelous
    1.76
    看著
    1.73
    梘
    1.73
    迓
    1.67
    をや
    1.66
    इटम
    1.65
    龵
    1.63
    靦
    1.60
    Activations Density 0.010%

    No Known Activations