© 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. 80876
    Prev
    Next
    INDEX
    Explanations

    advertisers reach increasing demand

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

    passion and violations

    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
    of
    0.56
    for
    0.54
    ration
    0.52
    three
    0.52
    ricted
    0.51
    five
    0.50
    é
    0.50
    ation
    0.49
     ثلاثة
    0.49
    to
    0.49
    POSITIVE LOGITS
     noss
    0.46
    𒉿
    0.45
    ᗜ
    0.44
    ᅱ
    0.44
     revise
    0.44
     lowers
    0.43
     উজ্জ্বল
    0.43
    ጕ
    0.43
    ўні
    0.42
    눙
    0.42
    Activations Density 0.001%

    No Known Activations