© 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. 169632
    Prev
    Next
    INDEX
    Explanations

    world to order

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

    lists and descriptions

    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
     AcOEt
    0.48
     लिखे
    0.46
     다음에
    0.45
     написа
    0.44
    哄
    0.44
     ಸಮಸ್ಯ
    0.43
     답변
    0.42
    粳
    0.42
     viết
    0.41
     Artículo
    0.41
    POSITIVE LOGITS
    ब्रिट
    0.48
     نړۍ
    0.48
     اسلح
    0.47
     welcomes
    0.46
     bravely
    0.46
     strives
    0.46
     urgently
    0.44
     azienda
    0.44
     ماشینونه
    0.43
     astute
    0.43
    Activations Density 0.001%

    No Known Activations