© 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. 31668
    Prev
    Next
    INDEX
    Explanations

    Recreation Area, scanned, switch

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

    steps and instructions

    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
    还有
    0.43
     Hiring
    0.43
    љи
    0.43
    湿度
    0.42
    teres
    0.42
    h
    0.41
     resale
    0.41
    ları
    0.41
    明确
    0.41
    <0xB1>
    0.40
    POSITIVE LOGITS
    OND
    0.57
     stanza
    0.53
     ರೀತಿಯ
    0.52
     ಎರಡು
    0.50
     ጥሩ
    0.50
     cherish
    0.50
     বয়স
    0.50
     সাবধান
    0.50
    GYPT
    0.49
     постара
    0.48
    Activations Density 0.000%

    No Known Activations