© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1573
    Prev
    Next
    INDEX
    Explanations

    and, or, int operators

    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_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
    Ancient
    0.95
     ancient
    0.94
    ancient
    0.90
     Biblical
    0.86
     önce
    0.84
     أف
    0.83
    璿
    0.83
    前に
    0.80
     எந்த
    0.79
     betul
    0.79
    POSITIVE LOGITS
     corresponding
    0.85
     naman
    0.80
    PositionY
    0.78
     afterwards
    0.77
     secund
    0.77
     afterward
    0.70
     subtract
    0.69
     conversely
    0.68
     other
    0.67
     outro
    0.62
    Activations Density 1.965%

    No Known Activations