© 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. 47416
    Prev
    Next
    INDEX
    Explanations

    numbers and awards

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

    option A

    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
     多い
    0.51
    วัสดี
    0.48
     IUnary
    0.47
     書い
    0.47
    вища
    0.45
     いた
    0.44
     ਐ
    0.44
     Сле
    0.44
     pengend
    0.44
    ItemLayout
    0.44
    POSITIVE LOGITS
    Didn
    0.53
    Doesn
    0.51
     Diner
    0.50
    don
    0.48
    -
    0.48
    '
    0.46
    天地
    0.45
     did
    0.44
     multiples
    0.43
    Won
    0.43
    Activations Density 0.000%

    No Known Activations