© 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. 165146
    Prev
    Next
    INDEX
    Explanations

    area measurements

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

    area in km² or sq mi

    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
     علیکم
    0.47
     stiffness
    0.44
     Serrurier
    0.43
     Stiffness
    0.43
     Quân
    0.41
     Flooring
    0.40
    骖
    0.39
    ニー
    0.38
     গলায়
    0.38
     dédié
    0.38
    POSITIVE LOGITS
     acreage
    0.43
     settling
    0.42
    судар
    0.41
    arrivals
    0.40
    opar
    0.40
    wide
    0.40
     settlements
    0.39
     statistical
    0.39
     scaled
    0.39
     neighborhoods
    0.38
    Activations Density 0.002%

    No Known Activations