© 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. 112248
    Prev
    Next
    INDEX
    Explanations

    activities and services

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

    languages other than English

    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
     Ս
    0.54
    기
    0.53
     コ
    0.50
     לג
    0.50
    타
    0.48
     ミ
    0.48
     cogeneration
    0.47
    まえ
    0.47
     ฮ
    0.46
     ми
    0.46
    POSITIVE LOGITS
    orio
    0.59
    lur
    0.57
    icit
    0.50
     Chub
    0.49
     Pretty
    0.48
     Dara
    0.48
    漂亮
    0.46
    lEdit
    0.45
    Julie
    0.44
    ڦ
    0.44
    Activations Density 0.000%

    No Known Activations