© 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. 116559
    Prev
    Next
    INDEX
    Explanations

    responsereturn shipping

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

    Wars, inclusion, explorers, angular

    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
    ക
    0.51
    鸞
    0.47
    ພວກເຮ
    0.47
    天井
    0.44
    ー
    0.44
    特定の
    0.44
    數字
    0.44
     triplets
    0.44
    し
    0.44
     軍
    0.43
    POSITIVE LOGITS
     resisted
    0.48
     halde
    0.46
     witnessed
    0.45
     earnestly
    0.45
    eflow
    0.45
    engl
    0.45
     kissed
    0.45
    ньше
    0.44
     estando
    0.44
    dert
    0.44
    Activations Density 0.000%

    No Known Activations