© 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. 2287
    Prev
    Next
    INDEX
    Explanations

    asking for details

    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
     édition
    0.38
     কথার
    0.36
     leben
    0.36
     není
    0.36
     Đây
    0.35
    ၊
    0.35
     fois
    0.34
    ياء
    0.33
     نباش
    0.33
    طا
    0.33
    POSITIVE LOGITS
     다음과
    0.45
     निम्नलिखित
    0.42
    :}
    0.41
    :
    0.41
     প্রথমেই
    0.39
    :</
    0.38
    would
    0.38
     şöyle
    0.37
     కొన్ని
    0.36
     sedikit
    0.36
    Activations Density 0.159%

    No Known Activations