© 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. 84710
    Prev
    Next
    INDEX
    Explanations

    added or improved items

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

    null and void

    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
     どう
    0.42
     एक्सच
    0.42
     cuánto
    0.42
     occupy
    0.41
     underdog
    0.41
     zuf
    0.40
     egregious
    0.40
     な
    0.40
     も
    0.40
     hopelessly
    0.40
    POSITIVE LOGITS
     GREEN
    0.50
     Booklet
    0.48
    是的
    0.48
     Coordinator
    0.46
     Wastewater
    0.46
    炁
    0.45
     Divisional
    0.45
     Stationery
    0.45
     মোঃ
    0.44
     Item
    0.44
    Activations Density 0.002%

    No Known Activations