© 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-262K
    7. 4731
    Prev
    Next
    INDEX
    Explanations

    use a

    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_262k_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
    อาจ
    0.24
     მაგრამ
    0.24
    andır
    0.23
     ngunit
    0.23
    但我
    0.22
    🗺
    0.22
    ién
    0.22
    ต้อง
    0.22
    andin
    0.22
    rası
    0.21
    POSITIVE LOGITS
     the
    0.55
     a
    0.48
     that
    0.42
     isang
    0.42
     an
    0.41
     one
    0.41
     two
    0.39
     einer
    0.38
     eine
    0.38
     this
    0.37
    Activations Density 1.181%

    No Known Activations