© 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. 7363
    Prev
    Next
    INDEX
    Explanations

    sentence start punctuation

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

    movie concepts

    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
    ๋
    0.42
     MATERIALS
    0.40
     বিষয়ক
    0.37
    )(
    0.36
    USES
    0.36
    ግብ
    0.35
     $($
    0.35
    ః
    0.34
    NAMES
    0.34
    様な
    0.34
    POSITIVE LOGITS
    ↵↵↵↵↵
    1.01
    ↵↵↵↵↵↵
    0.99
    ↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵
    0.91
    ↵↵↵↵↵↵↵↵
    0.89
    ↵↵↵↵↵↵↵↵↵
    0.89
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.88
    ↵↵↵↵↵↵↵↵↵↵
    0.88
    ↵↵↵↵
    0.86
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.84
    Activations Density 1.369%

    No Known Activations