© 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. 239497
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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
    binding
    0.46
     पहिला
    0.45
    ွန်
    0.44
    originally
    0.44
    bookings
    0.43
    最初は
    0.43
    computers
    0.43
    ❍
    0.43
     toget
    0.43
    結婚
    0.43
    POSITIVE LOGITS
    یسم
    0.51
     alert
    0.49
    ﺷ
    0.45
     a
    0.45
    েম্বর
    0.45
    шим
    0.45
     hausse
    0.44
     seismic
    0.44
     quelli
    0.43
    ری
    0.43
    Activations Density 0.001%

    No Known Activations