© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11567
    Prev
    Next
    INDEX
    Explanations

    polynomials `ax² + bx + c`

    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
    ibusdam
    1.23
     思い
    1.16
     हज़ार
    1.06
    漣
    1.03
    的人生
    1.02
    窿
    1.02
     mumkin
    1.02
     攵
    1.01
    ڏ
    0.99
    פת
    0.99
    POSITIVE LOGITS
     located
    0.69
     (
    0.69
    î
    0.67
     localização
    0.67
    exc
    0.63
     cele
    0.62
     allocate
    0.62
    销售
    0.61
    isten
    0.61
     élabor
    0.60
    Activations Density 0.001%

    No Known Activations