© 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. 133048
    Prev
    Next
    INDEX
    Explanations

    when selectingissue;on thevery muchExtraordinary Oils

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

    code and search queries

    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
    在地
    0.52
     crumbs
    0.42
     আনুগত্য
    0.42
    碱
    0.41
    ουμε
    0.40
     Dazu
    0.40
     ઉપયોગ
    0.40
    猗
    0.39
     Bookstore
    0.39
     ginh
    0.39
    POSITIVE LOGITS
    Rajasthan
    0.50
    ➝
    0.49
    nouns
    0.48
    オリジナル
    0.46
             
    0.45
    cover
    0.45
    +(
    0.44
    についての
    0.44
    =&
    0.44
    Chapter
    0.43
    Activations Density 0.002%

    No Known Activations