© 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. 52565
    Prev
    Next
    INDEX
    Explanations

    code generation

    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
     کیا۔
    0.41
    ከናወ
    0.40
    ού
    0.38
     lorry
    0.37
    （
    0.37
    лесо
    0.36
    ワー
    0.36
    скетбол
    0.36
    ൂ
    0.36
    ൌ
    0.36
    POSITIVE LOGITS
     AND
    0.44
    ЛИ
    0.39
     and
    0.37
    છા
    0.36
    chy
    0.35
     विभिन्न
    0.35
     пространство
    0.35
     الهمزه
    0.35
     valamint
    0.34
    ichen
    0.34
    Activations Density 0.118%

    No Known Activations