© 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. 4930
    Prev
    Next
    INDEX
    Explanations

    bird nests and nesting

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

    nested lists or recursion

    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
    宪
    0.42
    銓
    0.39
     टार
    0.38
    ᅯ
    0.37
    ಲಭ
    0.36
     संवैधानिक
    0.36
     psycho
    0.36
    Ꮜ
    0.36
    वानी
    0.35
    펍
    0.35
    POSITIVE LOGITS
     nest
    4.13
     nests
    3.81
     Nest
    3.78
     nesting
    3.75
     nested
    3.69
    Nest
    3.66
    nest
    3.61
     Nested
    3.41
    nested
    3.34
    Nested
    3.28
    Activations Density 0.055%

    No Known Activations