Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 66237
    Prev
    Next
    INDEX
    Explanations

    code structure and specialized terminology

    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_53_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
     então
    0.42
    则
    0.39
    द्रा
    0.39
    lasting
    0.38
    usive
    0.38
     entonces
    0.38
    usan
    0.37
     riverside
    0.37
    ടും
    0.37
    then
    0.37
    POSITIVE LOGITS
     _;
    0.49
     ρο
    0.40
     FY
    0.39
     isot
    0.39
    瞞
    0.37
    %)$
    0.37
     Lamin
    0.37
    輔
    0.37
     ప్ర
    0.36
     গ্যাস
    0.36
    Activations Density 0.002%

    No Known Activations