© 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. 22510
    Prev
    Next
    INDEX
    Explanations

    example, silver, collection, case

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

    examples and scenarios

    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
    pa
    0.45
    elin
    0.45
     Ett
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.43
    íd
    0.42
    vet
    0.42
     participating
    0.41
    olt
    0.41
    ora
    0.41
     $[
    0.41
    POSITIVE LOGITS
     svært
    0.49
     дней
    0.48
     kræ
    0.46
    ツイ
    0.44
     muốn
    0.44
     увагу
    0.44
     polypes
    0.44
     timers
    0.42
     ሰዎች
    0.42
     пользователи
    0.42
    Activations Density 0.000%

    No Known Activations