© 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. 2814
    Prev
    Next
    INDEX
    Explanations

    endings followed by punctuation

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

    terms followed by colon

    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
    。（
    0.59
    ～。
    0.57
     ہے۔
    0.50
    。",
    0.49
    。【
    0.48
     ہیں۔
    0.47
    。《
    0.46
    。</
    0.46
    .");
    0.45
     படத்தின்
    0.45
    POSITIVE LOGITS
    ↵↵
    0.50
    ness
    0.40
     I
    0.37
    )
    0.34
        
    0.34
            
    0.34
    ↵
    0.33
    +
    0.33
     B
    0.33
    0.32
    Activations Density 0.382%

    No Known Activations