© 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. 43693
    Prev
    Next
    INDEX
    Explanations

    reference works

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

    Early historical, philosophical, and programming concepts

    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
     paycheck
    0.48
    ាត់
    0.46
     blanchâtre
    0.46
     feeder
    0.45
     filet
    0.45
    2
    0.44
     funnel
    0.44
     cowboy
    0.44
     passer
    0.44
     filer
    0.43
    POSITIVE LOGITS
     எழுதிய
    0.51
     страница
    0.49
     ಅವರನ್ನು
    0.48
     affliction
    0.47
     религи
    0.47
    意识到
    0.47
    昦
    0.47
    🕌
    0.47
     यांना
    0.46
    踟
    0.46
    Activations Density 0.000%

    No Known Activations