© 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. 106735
    Prev
    Next
    INDEX
    Explanations

    slow cooker contents

    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
    стасия
    -0.75
    álló
    -0.73
    iveau
    -0.73
     Chaplin
    -0.72
     lubricant
    -0.71
    eci
    -0.71
    grap
    -0.70
    креп
    -0.69
     withstand
    -0.69
    优秀
    -0.68
    POSITIVE LOGITS
     slow
    1.62
    Slow
    1.41
     Slow
    1.40
     Crock
    1.35
    slow
    1.25
     crock
    1.25
     cooker
    1.03
     Instant
    0.97
     Pressure
    0.95
    Pressure
    0.94
    Activations Density 0.011%

    No Known Activations