© 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. 3716
    Prev
    Next
    INDEX
    Explanations

    sitting still or down

    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
    AutoField
    0.80
    érard
    0.77
    ก็
    0.77
    еро
    0.77
    ————————————————
    0.77
     অতএব
    0.77
    𝑙
    0.75
    西哥
    0.74
    gle
    0.73
    nextProps
    0.73
    POSITIVE LOGITS
    guru
    0.92
    belt
    0.89
     belts
    0.86
     resolv
    0.84
    ronics
    0.83
    ழ்
    0.81
     Revolutionary
    0.80
    чи
    0.80
     sat
    0.79
     resolución
    0.78
    Activations Density 0.088%

    No Known Activations