© 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. 143871
    Prev
    Next
    INDEX
    Explanations

    programming concepts or multilingual 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_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
    al
    0.44
    tellers
    0.44
     ควร
    0.43
    ና
    0.42
    systems
    0.42
    ean
    0.41
     waters
    0.41
    weeney
    0.40
    }\
    0.40
    aney
    0.40
    POSITIVE LOGITS
    Thời
    0.56
    ‌های
    0.53
     două
    0.53
     لڑ
    0.50
     Tablets
    0.50
    Бы
    0.49
    の説明
    0.48
    ời
    0.48
    obiles
    0.48
    Để
    0.46
    Activations Density 0.002%

    No Known Activations