© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13630
    Prev
    Next
    INDEX
    Explanations

    bootandy reboot nation

    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_40_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
    പൊ
    0.39
    らが
    0.38
    iça
    0.38
    s
    0.37
    o
    0.37
    Dirt
    0.36
     Front
    0.36
     Cust
    0.35
    t
    0.35
    親子
    0.35
    POSITIVE LOGITS
     boot
    0.62
    Boot
    0.62
     Boot
    0.59
     bootcamp
    0.59
     Bootcamp
    0.58
    boot
    0.55
     booting
    0.54
     booted
    0.50
    BOOT
    0.48
    leneck
    0.43
    Activations Density 0.010%

    No Known Activations