© 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-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1304
    Prev
    Next
    INDEX
    Explanations

    describing actions after commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     
    0.79
     You
    0.78
     It
    0.74
     Think
    0.74
     So
    0.70
     Everything
    0.66
     you
    0.66
     .
    0.64
     Gone
    0.64
     Anyway
    0.62
    POSITIVE LOGITS
     memberikan
    1.64
     meningkatkan
    1.42
     insbesondere
    1.39
     mengurangi
    1.36
     menawarkan
    1.32
     mendorong
    1.31
    并在
    1.30
     menyediakan
    1.30
     memperoleh
    1.30
    그리고
    1.29
    Activations Density 0.990%

    No Known Activations