© 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. 79478
    Prev
    Next
    INDEX
    Explanations

    again later

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

    try again

    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
    return
    0.53
    3
    0.49
    Common
    0.46
    Prepare
    0.45
    PROGRAM
    0.45
    Custom
    0.44
    ace
    0.44
    bcb
    0.43
    of
    0.43
    Disease
    0.43
    POSITIVE LOGITS
    겉
    0.47
     cabaret
    0.45
    лку
    0.44
    між
    0.44
    დი
    0.44
    
    0.43
     cheering
    0.43
    বারে
    0.42
    נות
    0.42
    데요
    0.42
    Activations Density 0.001%

    No Known Activations