© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2249
    Prev
    Next
    INDEX
    Explanations

    dive in or into

    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_16k_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
     東
    0.33
    }}+\
    0.32
    iciens
    0.31
    ellan
    0.31
    ajou
    0.30
     डाइऑक्साइड
    0.30
    ?’”
    0.29
    ươi
    0.29
     기반
    0.29
     말미암
    0.29
    POSITIVE LOGITS
    з
    0.43
    ز
    0.42
     to
    0.42
     onto
    0.41
    ээ
    0.38
     quickly
    0.38
     immediately
    0.38
     hızlı
    0.38
     QUICK
    0.38
     into
    0.37
    Activations Density 0.118%

    No Known Activations