© 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. 201247
    Prev
    Next
    INDEX
    Explanations

    appealed to

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

    visual descriptions and abstract qualities

    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
    le
    0.47
    len
    0.47
    t
    0.45
    week
    0.43
    #
    0.43
     drinkers
    0.43
    %
    0.43
    sgn
    0.43
    allow
    0.42
    den
    0.41
    POSITIVE LOGITS
     미술
    0.50
    ეფ
    0.46
    坚定
    0.45
    敔
    0.45
     அம்ச
    0.44
     فريق
    0.44
    敉
    0.44
    牺
    0.43
     متعلقه
    0.43
    戽
    0.43
    Activations Density 0.000%

    No Known Activations