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. 16-GEMMASCOPE-2-RES-262K
    4. 5162
    Prev
    Next
    INDEX
    Explanations

    heart of [number]

    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_16_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
    ח
    0.60
    ก
    0.60
    ע
    0.59
     mocks
    0.57
    न
    0.57
    ש
    0.57
     academies
    0.57
    ן
    0.55
    い
    0.49
    ین
    0.49
    POSITIVE LOGITS
     მიმო
    0.63
    comings
    0.62
     温度
    0.55
    ܀
    0.55
    トラック
    0.53
     Predicted
    0.53
    estimated
    0.53
    calculated
    0.53
    カテゴリ
    0.53
    jud
    0.52
    Activations Density 0.000%

    No Known Activations