© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 20758
    Prev
    Next
    INDEX
    Explanations

    UN Security Council resolutions and relations

    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_16_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
    städ
    0.59
    迢
    0.59
    మైన
    0.57
    識別
    0.55
    Site
    0.55
    kov
    0.54
    బ్యా
    0.54
    ");*/
    0.54
    أ
    0.54
    ters
    0.54
    POSITIVE LOGITS
    ר
    0.84
    er
    0.83
     b
    0.75
     perceptive
    0.72
     reminds
    0.71
     rog
    0.71
     enhances
    0.66
     диамет
    0.66
     memb
    0.66
     puncak
    0.66
    Activations Density 0.001%

    No Known Activations