© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 55930
    Prev
    Next
    INDEX
    Explanations

    automate, integrate, create

    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
     Thankfully
    0.45
    这本书
    0.42
     এটা
    0.41
     Aged
    0.41
     الكتب
    0.41
     إدارة
    0.41
     這個
    0.41
    ۔
    0.41
    Eden
    0.41
     هذا
    0.40
    POSITIVE LOGITS
    };
    0.44
    nym
    0.43
    gency
    0.42
    nogo
    0.41
     consecutive
    0.41
    owy
    0.40
    asting
    0.40
    atán
    0.40
    மற்ற
    0.39
    šení
    0.39
    Activations Density 0.019%

    No Known Activations