© 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. 36932
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    quirky personalities, critical, fast

    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
     radionuclide
    0.47
    ⮚
    0.47
    ঙ্গিক
    0.43
     omnichannel
    0.41
    τικό
    0.41
     युवकों
    0.40
     institutions
    0.40
    大学
    0.40
     Collider
    0.40
     universit
    0.39
    POSITIVE LOGITS
     наста
    0.44
     vises
    0.44
     পারিল
    0.43
     уто
    0.42
     шири
    0.42
    𝙜
    0.41
     ошиб
    0.40
     числен
    0.39
     પ્રસ
    0.39
     використову
    0.39
    Activations Density 0.000%

    No Known Activations