© 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. 44495
    Prev
    Next
    INDEX
    Explanations

    irregular linguistic markers

    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
    ர்ச்சி
    0.45
    ὖ
    0.44
    批
    0.44
    Ᏸ
    0.42
    Видео
    0.42
     áng
    0.42
    Prothorax
    0.42
    敔
    0.42
     फॉलोइंग
    0.41
    тра
    0.41
    POSITIVE LOGITS
    ،
    0.52
     Jahre
    0.47
     و
    0.47
     poate
    0.47
     modeli
    0.47
     පිළිබඳ
    0.47
     puede
    0.46
    accus
    0.46
     controversies
    0.45
    informed
    0.45
    Activations Density 0.002%

    No Known Activations