© 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. 53-GEMMASCOPE-2-RES-262K
    7. 14527
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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_53_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
    
    0.38
    ंदरे
    0.37
    
    0.37
    wall
    0.36
    ︿
    0.36
    想想
    0.36
    বসাইট
    0.35
    বিস্তারিত
    0.35
    Ḍ
    0.35
    രാണ്
    0.35
    POSITIVE LOGITS
    ;
    2.09
    ；
    1.90
     ;
    1.88
    ;\
    1.81
    ؛
    1.81
    ;"
    1.75
    ;')
    1.71
    ;(
    1.69
    ;")
    1.69
     ؛
    1.67
    Activations Density 0.067%

    No Known Activations