© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53245
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ूती
    0.42
     aparecen
    0.41
    boxed
    0.40
    cza
    0.39
     Ð
    0.39
    zl
    0.39
     boxed
    0.39
    M
    0.39
    datac
    0.38
    ক্ষিপ্ত
    0.38
    POSITIVE LOGITS
    ።
    0.56
    ም።
    0.51
    ။
    0.49
    ว่า
    0.47
    。
    0.47
    ไม่มี
    0.47
    ۔
    0.47
    ᒻ
    0.46
    ል።
    0.46
    อิน
    0.46
    Activations Density 0.007%

    No Known Activations