© 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. 17372
    Prev
    Next
    INDEX
    Explanations

    unwinding, rewrote, unwound

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

    rewrites and rewriting

    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
    WP
    0.53
    ny
    0.50
    W
    0.50
    WT
    0.49
    WW
    0.48
    ww
    0.48
    𝑤
    0.48
    wn
    0.47
    WY
    0.47
     wz
    0.47
    POSITIVE LOGITS
     unw
    0.52
     unwind
    0.44
    irte
    0.43
     rit
    0.42
     Rew
    0.41
     view
    0.40
    टिंग
    0.40
     View
    0.40
     rap
    0.40
    riting
    0.39
    Activations Density 0.008%

    No Known Activations