© 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. 204784
    Prev
    Next
    INDEX
    Explanations

    data-driven initiatives

    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
     ₽
    0.45
     Đấy
    0.42
    >\<^
    0.42
     ინტერ
    0.42
     kise
    0.42
    ⌜
    0.41
    椋
    0.41
    ewöhn
    0.41
     Bundest
    0.41
    ²',
    0.40
    POSITIVE LOGITS
     render
    0.40
     looting
    0.39
    اف
    0.38
    Form
    0.38
    Appear
    0.38
     rendered
    0.37
     salvage
    0.37
    Jamie
    0.37
    شر
    0.36
    一生
    0.36
    Activations Density 0.057%

    No Known Activations