© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3767
    Prev
    Next
    INDEX
    Explanations

    Captain America

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

    Returns: or descriptions explaining code

    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
    .[/
    0.45
    。「
    0.45
    <unused2121>
    0.42
    <0xC2>
    0.41
    <unused2172>
    0.40
    getDefaultSh
    0.39
    。《
    0.37
    。『
    0.37
    。",
    0.36
     Nederlands
    0.35
    POSITIVE LOGITS
    ↵
    1.01
    ‬
    0.70
     、,
    0.68
    <0x0D>
    0.63
    
    0.57
    ↵↵
    0.55
    </h2>
    0.46
    </span>
    0.45
                  
    0.44
    ';...
    0.44
    Activations Density 0.632%

    No Known Activations