© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 41299
    Prev
    Next
    INDEX
    Explanations

    punctuation after generic text

    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_16_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
    <
    0.68
    ن
    0.59
    도
    0.56
    lid
    0.55
    id
    0.55
     theses
    0.53
    ü
    0.53
    *
    0.53
     Guest
    0.52
    лені
    0.52
    POSITIVE LOGITS
     партия
    0.65
     требуют
    0.62
     PVA
    0.59
     שלה
    0.59
     খুব
    0.58
     प्रशिक्षण
    0.58
    ๙
    0.57
     песен
    0.57
     لیکن
    0.57
     свои
    0.56
    Activations Density 0.003%

    No Known Activations