© 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. 216599
    Prev
    Next
    INDEX
    Explanations

    permanently, chair, Services, salary, transition

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

    keywords, formats, separators

    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
     Herbs
    0.46
    色は
    0.44
    秋冬
    0.44
    杏
    0.43
    แผน
    0.42
    儿童
    0.41
     infring
    0.40
     infringe
    0.40
    大型
    0.40
    翻訳
    0.40
    POSITIVE LOGITS
    rictor
    0.49
     Иногда
    0.48
     바로
    0.46
     Много
    0.45
     Ս
    0.45
     Джей
    0.45
     Дж
    0.44
     지난
    0.43
     ಕಳೆದ
    0.42
     Бан
    0.42
    Activations Density 0.000%

    No Known Activations