© 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. 139584
    Prev
    Next
    INDEX
    Explanations

    adjudicated to

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

    rights law, Business Alignment

    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
     دوسرے
    0.54
     другим
    0.50
     možno
    0.49
    يكون
    0.48
     jei
    0.48
    ｖ
    0.47
     മറ്റു
    0.47
     الاجتماعية
    0.47
    物質
    0.46
     সমাজ
    0.46
    POSITIVE LOGITS
    ുകള
    0.48
    Parse
    0.44
    clear
    0.43
    ައ
    0.43
    Editable
    0.42
    는
    0.42
     Parsing
    0.40
    )`,
    0.39
    ;",
    0.39
    =")
    0.39
    Activations Density 0.001%

    No Known Activations