© 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. 209378
    Prev
    Next
    INDEX
    Explanations

    lists of items, specifications, or options

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

    synchronized

    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
     只
    0.49
    াপন্ন
    0.48
     ንጥረ
    0.48
     Character
    0.47
    StringEncoding
    0.46
     σε
    0.46
     রোগের
    0.46
     学
    0.46
     」,
    0.45
     يع
    0.45
    POSITIVE LOGITS
     mitad
    0.54
    former
    0.49
    ers
    0.48
     greens
    0.47
    정과
    0.46
     carefree
    0.45
    戝
    0.44
     PCI
    0.44
     Phyllis
    0.44
    ارق
    0.44
    Activations Density 0.001%

    No Known Activations