© 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. 192120
    Prev
    Next
    INDEX
    Explanations

    place names and destinations

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

    code snippets

    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
     ironically
    0.49
    우
    0.49
     Eun
    0.44
     Jimmy
    0.43
     Yin
    0.43
     A
    0.42
     appare
    0.42
     frequ
    0.41
     Kim
    0.41
     Business
    0.41
    POSITIVE LOGITS
     dní
    0.54
     není
    0.53
    শাসন
    0.52
     nooit
    0.52
     został
    0.52
    łącznie
    0.51
    ীশ
    0.51
    쇤
    0.49
    쾨
    0.49
    ভিয়েতনাম
    0.47
    Activations Density 0.001%

    No Known Activations