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. 82829
    Prev
    Next
    INDEX
    Explanations

    Toronto Maple Leafs

    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
    VQ
    0.43
    فهام
    0.42
     শিল্প
    0.42
     मम
    0.41
    கோவை
    0.40
    ÑO
    0.38
     ഗുരു
    0.38
    断
    0.38
     Peoria
    0.38
     شيء
    0.38
    POSITIVE LOGITS
    Leaf
    0.93
     leaf
    0.87
     Leaf
    0.84
     Maple
    0.77
    leaf
    0.76
    Maple
    0.70
     maple
    0.68
     leafs
    0.65
     Leafs
    0.59
     leafy
    0.58
    Activations Density 0.002%

    No Known Activations