© 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
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 328
    Prev
    Next
    INDEX
    Explanations

    instruction, code, or prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    с
    0.57
     е
    0.57
     се
    0.56
     बहुतेक
    0.56
     ដែល
    0.54
     ने
    0.54
     Во
    0.53
     は
    0.52
     yang
    0.51
    :
    0.51
    POSITIVE LOGITS
    ূপে
    0.60
     Distillery
    0.59
     Architectural
    0.58
     Bibliography
    0.58
     xas
    0.58
     ilç
    0.58
     Development
    0.57
    Development
    0.57
    isać
    0.57
    澶
    0.57
    Activations Density 0.124%

    No Known Activations