© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139517
    Prev
    Next
    INDEX
    Explanations

    lifetime residential

    np_acts-logits-general · gemini-2.5-flash-lite

    formulas and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zayn
    0.48
    IRD
    0.47
     Assistant
    0.47
     Weird
    0.47
     Parks
    0.46
     Campground
    0.46
     Interference
    0.45
    翊
    0.44
     Creativity
    0.44
     Stadium
    0.44
    POSITIVE LOGITS
     मायणी
    0.49
     deviations
    0.49
     variabel
    0.49
     cooling
    0.48
    cooling
    0.48
     lowest
    0.48
    ှ
    0.47
     thread
    0.47
     tensile
    0.46
     rotary
    0.46
    Activations Density 0.005%

    No Known Activations