© 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-65K
    7. 49167
    Prev
    Next
    INDEX
    Explanations

    best quality, ultra detailed, new

    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_65k_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
    ুস
    0.42
    封面
    0.39
     Здравствуйте
    0.39
     Containing
    0.39
     MANUFACTURING
    0.38
    赶
    0.38
    CONTACT
    0.37
     sloping
    0.37
    फ
    0.37
     শ্র
    0.37
    POSITIVE LOGITS
     جديد
    0.51
     toolkit
    0.48
     outfit
    0.46
     new
    0.45
     новый
    0.43
     انڈیا
    0.43
     unscathed
    0.43
     transaksi
    0.42
     جدید
    0.41
     Kanada
    0.41
    Activations Density 0.016%

    No Known Activations