© 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. 107340
    Prev
    Next
    INDEX
    Explanations

    filter, destination, check, menu, children

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

    relies on, requires, from

    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
     barns
    0.51
    lname
    0.50
     specialties
    0.46
    罰
    0.46
    barn
    0.46
     financed
    0.45
    lé
    0.44
     DNS
    0.44
    berge
    0.44
     destroy
    0.43
    POSITIVE LOGITS
    Unexpected
    0.50
    Recommended
    0.48
    Hik
    0.46
    Trending
    0.46
    ۰
    0.46
    Crossing
    0.44
    த்தர
    0.44
    兎
    0.43
     Lettuce
    0.41
    创建一个
    0.41
    Activations Density 0.000%

    No Known Activations