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. 31-GEMMASCOPE-2-RES-262K
    4. 16391
    Prev
    Next
    INDEX
    Explanations

    Meteorological Organization

    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_31_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
     apologize
    0.44
    胳
    0.43
    性和
    0.43
    ቶችን
    0.42
    이미
    0.42
    镯
    0.42
    的样子
    0.41
    겠지만
    0.40
     padlock
    0.40
     inactivity
    0.40
    POSITIVE LOGITS
     הס
    0.53
     בית
    0.51
    ONU
    0.50
    ๘
    0.49
     בין
    0.47
    AKA
    0.46
     สุด
    0.46
    ฆ
    0.46
    ALL
    0.46
     மத
    0.46
    Activations Density 0.001%

    No Known Activations