© 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. 65193
    Prev
    Next
    INDEX
    Explanations

    specific conditions and states

    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
     ambivalent
    0.43
     supr
    0.39
     Asp
    0.38
     
    0.37
     ges
    0.37
     décro
    0.37
     Sup
    0.36
     superior
    0.36
     upright
    0.35
    Ges
    0.35
    POSITIVE LOGITS
    ۣ
    0.42
    öny
    0.41
    ölt
    0.39
    ेटेड
    0.39
     ವಿಧಾನ
    0.39
    áról
    0.38
    ুদ্ধে
    0.38
    こちら
    0.38
    佾
    0.38
    สเตอร์
    0.37
    Activations Density 0.001%

    No Known Activations