© 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. 49151
    Prev
    Next
    INDEX
    Explanations

    positive earnings

    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
     membeli
    0.49
     mercados
    0.48
     perdagangan
    0.46
     markets
    0.46
     bankers
    0.46
     dün
    0.45
     снова
    0.45
    𝘬
    0.45
     नरम
    0.44
     dahil
    0.44
    POSITIVE LOGITS
    radiation
    0.43
    不能为空
    0.40
     apprehension
    0.39
     Zacks
    0.39
    穎
    0.39
    usive
    0.39
    nour
    0.39
    )},\
    0.39
    ingles
    0.39
    traits
    0.39
    Activations Density 0.009%

    No Known Activations