© 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. 134004
    Prev
    Next
    INDEX
    Explanations

    laws, prompts, playfully admitting

    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
    Their
    0.38
    Egg
    0.38
     τους
    0.38
    🐑
    0.38
    🎐
    0.37
     მათ
    0.37
    Eggs
    0.37
    皁
    0.36
     announcement
    0.36
    σον
    0.36
    POSITIVE LOGITS
    okas
    0.41
    педи
    0.40
    weapons
    0.39
    hovah
    0.39
     weapons
    0.38
     ابي
    0.38
    xer
    0.38
    rmi
    0.38
     Счет
    0.38
     PNG
    0.36
    Activations Density 0.000%

    No Known Activations