© 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-262K
    7. 71486
    Prev
    Next
    INDEX
    Explanations

    ssh keys or scope

    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_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
     स्थिति
    0.44
     социа
    0.44
    邇
    0.44
    ٥
    0.44
    調
    0.42
    國家
    0.41
    誰
    0.40
     মানুষ
    0.40
     वैज्ञानिक
    0.39
    [\
    0.39
    POSITIVE LOGITS
    
    0.51
    ikti
    0.51
     naturale
    0.49
    
    0.47
     naturelle
    0.46
     eût
    0.45
     kogu
    0.44
     anul
    0.44
     DAS
    0.44
     עס
    0.44
    Activations Density 0.001%

    No Known Activations