© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47020
    Prev
    Next
    INDEX
    Explanations

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ن
    0.48
    اخ
    0.47
    न
    0.42
    forall
    0.41
     creativity
    0.40
    vary
    0.40
    ا
    0.40
    ح
    0.39
    مه
    0.39
     entertainment
    0.39
    POSITIVE LOGITS
     ระบบ
    0.52
     ውጤ
    0.47
     সৌমিত্র
    0.47
    ্লিকেশন
    0.46
     נו
    0.45
     мастера
    0.45
    TorpedoStore
    0.44
     เนื่องจาก
    0.44
     จาก
    0.44
     тэ
    0.44
    Activations Density 0.016%

    No Known Activations