© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 190603
    Prev
    Next
    INDEX
    Explanations

    foreign languages and names

    np_acts-logits-general · gemini-2.5-flash-lite

    character recognition, or specific metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    のが
    0.59
     উদ্ভিদ
    0.53
    のは
    0.52
    ꫝ
    0.49
    inis
    0.47
    UEFA
    0.46
    base
    0.46
    ika
    0.46
    တို့ကို
    0.46
    🤎
    0.46
    POSITIVE LOGITS
     screech
    0.48
    ilizce
    0.48
     LINKS
    0.47
     Sliding
    0.46
    两个人
    0.46
     క్ర
    0.45
     hands
    0.44
     समिट
    0.44
     Crimean
    0.44
     Working
    0.43
    Activations Density 0.000%

    No Known Activations