© 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. 38861
    Prev
    Next
    INDEX
    Explanations

    coffee beans expansion

    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
     jedynie
    0.48
    શી
    0.43
     σημαν
    0.42
    っている
    0.40
    ట్స్‌మన్
    0.40
     तुला
    0.40
    鉾
    0.40
    僞
    0.39
     belie
    0.39
    niejszych
    0.39
    POSITIVE LOGITS
    ొ
    0.47
    g
    0.46
     Dal
    0.42
    corona
    0.41
    ıc
    0.41
     nếu
    0.41
     وطالبات
    0.41
    0.40
     Packing
    0.40
    Booking
    0.39
    Activations Density 0.003%

    No Known Activations