© 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. 13047
    Prev
    Next
    INDEX
    Explanations

    generally if

    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
    गो
    0.39
     Dynamic
    0.38
    Warm
    0.38
    具
    0.38
     мг
    0.37
    暖かい
    0.37
    Cream
    0.37
    noc
    0.37
    柑
    0.37
    素敵な
    0.37
    POSITIVE LOGITS
     získ
    0.51
     began
    0.47
    
    0.43
     extremist
    0.41
     discouraged
    0.39
     จน
    0.39
     começou
    0.39
     desenvolvimento
    0.38
     undertook
    0.38
     ಸ್ವಲ್ಪ
    0.38
    Activations Density 0.034%

    No Known Activations