© 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. 5764
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
     شناخته
    0.45
    }--
    0.43
     بگ
    0.42
    ก็จะ
    0.42
     оказыва
    0.40
     น้ำ
    0.40
     ਤੁ
    0.40
    ”、
    0.40
     ока
    0.39
     არა
    0.39
    POSITIVE LOGITS
     is
    0.52
     {//
    0.50
    throws
    0.46
    ？
    0.45
     has
    0.43
    ियर
    0.43
    ؟!
    0.43
     Μαρ
    0.43
     {
    0.42
    is
    0.41
    Activations Density 0.057%

    No Known Activations