© 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-65K
    7. 9793
    Prev
    Next
    INDEX
    Explanations

    tasks and concurrency

    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_65k_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
     colorless
    0.43
     oon
    0.43
     Clifford
    0.39
    ൩
    0.39
    toare
    0.38
    ḧ
    0.38
    ᱶ
    0.38
    peuta
    0.38
     indo
    0.37
    ార్లు
    0.37
    POSITIVE LOGITS
    ↵↵
    0.46
    ↵↵↵
    0.43
     Оба
    0.41
     ע
    0.40
    เรา
    0.39
    ელ
    0.38
    ยาง
    0.38
    ся
    0.37
    तरी
    0.37
     Exel
    0.37
    Activations Density 0.002%

    No Known Activations