© 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. 4711
    Prev
    Next
    INDEX
    Explanations

    half, first, second

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

    half

    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
    ≣
    0.35
    ंतिक
    0.34
    वले
    0.33
    থম
    0.31
    ܩ
    0.31
    ถมศึกษา
    0.30
    assung
    0.30
    igat
    0.30
    ೀತ
    0.30
     যুগে
    0.30
    POSITIVE LOGITS
     half
    5.09
     Half
    4.78
    Half
    4.75
    half
    4.69
     HALF
    4.53
    HALF
    4.22
    半
    4.22
     نصف
    4.06
     полови
    3.83
     setengah
    3.81
    Activations Density 0.384%

    No Known Activations