© 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-262K
    7. 47189
    Prev
    Next
    INDEX
    Explanations

    near candles

    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
    רי
    0.28
    פ
    0.26
     social
    0.24
    ва
    0.24
    хи
    0.23
    твор
    0.23
    ﻌ
    0.23
    жи
    0.23
     political
    0.23
     convivial
    0.23
    POSITIVE LOGITS
    如果你
    0.30
     如果
    0.29
     Nếu
    0.28
     använder
    0.27
     Eğer
    0.27
     χρησιμοποι
    0.26
     verwenden
    0.26
    を使用
    0.26
    ），
    0.25
     Jeśli
    0.25
    Activations Density 0.122%

    No Known Activations