© 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. 249173
    Prev
    Next
    INDEX
    Explanations

    south korea ads

    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
     संरक्षक
    0.52
     మూ
    0.50
     заго
    0.50
    至于
    0.50
     بِ
    0.49
    肐
    0.49
     कार्यों
    0.48
    телю
    0.48
    ▦
    0.47
     సహాయ
    0.47
    POSITIVE LOGITS
     moins
    0.44
    Bar
    0.44
    Ci
    0.43
    man
    0.43
    mimpi
    0.43
    TC
    0.42
    Remote
    0.42
     cart
    0.42
    Factory
    0.40
     remote
    0.40
    Activations Density 0.000%

    No Known Activations