© 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. 31-GEMMASCOPE-2-RES-65K
    7. 52524
    Prev
    Next
    INDEX
    Explanations

    improved mental clarity

    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_31_width_65k_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
    하는
    0.50
     සැල
    0.46
    扛
    0.46
    무
    0.46
     무
    0.45
     رز
    0.45
    还没有
    0.43
     комиссии
    0.43
     برای
    0.42
    ллер
    0.42
    POSITIVE LOGITS
    ლებიც
    0.46
     salut
    0.44
    ்டு
    0.44
    áni
    0.41
    ʟ
    0.41
    వెట్‌
    0.40
     nyc
    0.40
     normale
    0.40
    الحضور
    0.40
     promulgating
    0.40
    Activations Density 0.019%

    No Known Activations