© 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. 195735
    Prev
    Next
    INDEX
    Explanations

    evening pier

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

    willingly choosing

    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
     последние
    0.43
    ﺒ
    0.43
     demand
    0.42
     consequatur
    0.42
     upland
    0.41
     assumptive
    0.41
     بع
    0.40
     последнее
    0.40
     vea
    0.40
     foreclosure
    0.40
    POSITIVE LOGITS
    metaTag
    0.52
    쩝
    0.49
    onOptions
    0.49
    getTitle
    0.47
     Wörter
    0.47
    ＠
    0.46
    ({"
    0.46
    Შ
    0.46
    entrum
    0.46
     Kommentar
    0.45
    Activations Density 0.000%

    No Known Activations