© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11788
    Prev
    Next
    INDEX
    Explanations

    punctuation and surrounding symbols

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

    client initialization

    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_40_width_16k_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
    x
    0.43
    ?')
    0.41
    ref
    0.40
    ja
    0.40
    iese
    0.40
    rok
    0.39
    rich
    0.38
    armed
    0.38
    feri
    0.38
    !).
    0.38
    POSITIVE LOGITS
    。(
    0.43
     ไม่มี
    0.40
    。（
    0.40
     ():
    0.39
     🙂
    0.38
    どうぞ
    0.37
    ↵↵↵↵
    0.37
    ။
    0.37
     ();
    0.37
    ។
    0.37
    Activations Density 0.358%

    No Known Activations