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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 224341
    Prev
    Next
    INDEX
    Explanations

    American football and technical terms

    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_40_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
     universities
    0.38
     Asa
    0.37
     important
    0.37
    兎
    0.37
    Ux
    0.36
    승
    0.36
     unemployment
    0.36
    াসা
    0.35
     இரவு
    0.35
    ވާ
    0.35
    POSITIVE LOGITS
    มัน
    0.45
     આમ
    0.42
    謐
    0.40
    ontan
    0.39
    strcmp
    0.37
     Radiological
    0.37
    混凝土
    0.37
    它
    0.36
     सम्प
    0.36
     它
    0.36
    Activations Density 0.001%

    No Known Activations