© 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. 40-GEMMASCOPE-2-RES-65K
    7. 722
    Prev
    Next
    INDEX
    Explanations

    parameter assignments

    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_40_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
     transfusion
    0.38
     খেয়ে
    0.37
     dieta
    0.36
    Hydroxy
    0.35
    CopyWith
    0.35
    oconut
    0.35
    洁
    0.34
    াহরণ
    0.34
    Eddie
    0.34
    Heather
    0.34
    POSITIVE LOGITS
    =
    0.93
    ="
    0.87
    ='
    0.64
    =\
    0.58
    =”
    0.57
    =${
    0.55
    :"
    0.54
    ="")
    0.54
    ={
    0.54
    =$
    0.52
    Activations Density 0.241%

    No Known Activations