© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1563
    Prev
    Next
    INDEX
    Explanations

    as stored billing

    np_acts-logits-general · gemini-2.5-flash-lite

    portray precisely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    7
    0.47
     Commonly
    0.41
     seventy
    0.41
    
    0.41
    specifiedByURL
    0.39
    ۷
    0.39
    водитель
    0.38
    ="../../
    0.37
     heartily
    0.37
     insinu
    0.37
    POSITIVE LOGITS
     ٹ
    0.46
    กัด
    0.44
     ২৬
    0.42
     ejercer
    0.41
    плення
    0.41
     যন্ত্রপাতি
    0.41
     ट
    0.41
    ২৬
    0.41
    ২৯
    0.40
     ৬
    0.40
    Activations Density 0.393%

    No Known Activations