© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7190
    Prev
    Next
    INDEX
    Explanations

    box, corner, area

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

    core principles, expert knowledge, labeled data

    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
    "]}
    0.39
    在日本
    0.39
    "};
    0.36
    }",
    0.35
    மக்கு
    0.35
    在中国
    0.35
    Q
    0.35
    史上
    0.34
    aje
    0.33
    rocław
    0.33
    POSITIVE LOGITS
     Beatles
    0.54
     Scientology
    0.52
     Wildcats
    0.51
     Mycobacterium
    0.50
     Shimano
    0.48
     Buccaneers
    0.47
     Hezbollah
    0.47
     Cavs
    0.46
     Skyrim
    0.46
     Gazprom
    0.45
    Activations Density 0.528%

    No Known Activations