© 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. 6175
    Prev
    Next
    INDEX
    Explanations

    explaining topics with abbreviations

    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
     Primeiro
    0.43
    ۲۰
    0.43
     Banda
    0.42
    dari
    0.41
    ۵
    0.41
     lanjutan
    0.41
     Tugas
    0.41
    ïne
    0.41
     ساختمان
    0.41
    middels
    0.41
    POSITIVE LOGITS
     intercellular
    0.38
    きたい
    0.37
    部分
    0.35
     replen
    0.35
    不易
    0.35
     হোক
    0.35
     decorations
    0.34
    ခ
    0.34
     suppressed
    0.34
     potentially
    0.33
    Activations Density 0.069%

    No Known Activations