© 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. 245781
    Prev
    Next
    INDEX
    Explanations

    cast, direction, finish, excess, completed

    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
     архі
    0.51
    Архі
    0.50
    Arch
    0.48
    ('/
    0.46
    Analytical
    0.44
     aisément
    0.44
    溃
    0.44
    High
    0.43
     квіт
    0.43
     specjal
    0.43
    POSITIVE LOGITS
     phim
    0.49
    ంది
    0.47
    榜
    0.46
     ресторан
    0.45
    勒
    0.43
    。
    0.43
    รายการ
    0.42
    rafish
    0.42
    ემ
    0.41
    "])
    0.41
    Activations Density 0.000%

    No Known Activations