© 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. 51439
    Prev
    Next
    INDEX
    Explanations

    from all

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

    information derived or identified

    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
     socialist
    0.48
     તથા
    0.48
    ྙ
    0.46
    佗
    0.45
     カード
    0.45
     Radical
    0.43
    玧
    0.43
     ხელისუფლების
    0.43
    BTC
    0.42
    ذور
    0.42
    POSITIVE LOGITS
     rétréci
    0.48
     উদ্ধার
    0.46
     it
    0.43
     récupérer
    0.40
    स्तों
    0.40
     بہتر
    0.39
    甩
    0.39
     threw
    0.39
     بھر
    0.39
     trainings
    0.39
    Activations Density 0.000%

    No Known Activations