© 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. 46984
    Prev
    Next
    INDEX
    Explanations

    Names, titles, and labels

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

    labels and headings

    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
     வருவத
    0.41
     якщо
    0.41
    තර
    0.40
    ^{-(
    0.39
    Voir
    0.39
    Note
    0.37
     pokud
    0.37
     ],
    0.37
    ものが
    0.37
    ಓ
    0.37
    POSITIVE LOGITS
    ：
    0.73
    :
    0.68
    ؛
    0.60
    ::
    0.57
    ︰
    0.56
     Name
    0.54
    ：“
    0.54
    ː
    0.54
    ៖
    0.54
    name
    0.53
    Activations Density 0.019%

    No Known Activations