© 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. 46769
    Prev
    Next
    INDEX
    Explanations

    on top of

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

    top of

    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
    ی
    0.66
    Ἥ
    0.63
    ע
    0.62
     وکړئ
    0.61
     amiable
    0.61
     embassies
    0.61
     protiv
    0.60
    ১
    0.60
     companions
    0.59
     وړاندوینې
    0.59
    POSITIVE LOGITS
    top
    1.04
    it
    0.92
    as
    0.86
    topping
    0.83
     topp
    0.82
    。
    0.79
    to
    0.78
    o
    0.77
    over
    0.77
    ta
    0.77
    Activations Density 0.031%

    No Known Activations