© 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. 152390
    Prev
    Next
    INDEX
    Explanations

    services and bios

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

    categories and structures

    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
    import
    0.52
     програм
    0.46
     miser
    0.44
    id
    0.44
    cription
    0.43
     lyr
    0.43
    
    0.42
     memorize
    0.42
    idam
    0.42
     McQu
    0.41
    POSITIVE LOGITS
     positifs
    0.51
     apparaître
    0.49
     Règles
    0.48
    ချက်
    0.47
    သား
    0.45
    ဖွဲ့
    0.44
     postérieurs
    0.44
    🍢
    0.44
     κάνει
    0.44
     असतात
    0.44
    Activations Density 0.001%

    No Known Activations