© 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. 57027
    Prev
    Next
    INDEX
    Explanations

    co relating to joint actions

    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
     sleeper
    0.45
    尔
    0.42
    ೂರ
    0.39
    ל
    0.39
    徹
    0.39
    ᓕ
    0.38
    新鲜
    0.38
    固体
    0.38
     l
    0.37
     fie
    0.37
    POSITIVE LOGITS
     co
    1.12
     совме
    0.94
     jointly
    0.93
     joint
    0.91
    joint
    0.91
     공동
    0.86
    ร่วม
    0.84
     सह
    0.82
     współ
    0.78
     совместно
    0.76
    Activations Density 0.056%

    No Known Activations