© 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-262K
    7. 50850
    Prev
    Next
    INDEX
    Explanations

    generic framework

    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_262k_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
     nylon
    0.51
     nutrition
    0.50
     C
    0.47
     water
    0.46
     COVID
    0.45
     N
    0.45
     catheter
    0.45
     P
    0.44
     R
    0.44
     mechanical
    0.44
    POSITIVE LOGITS
     політи
    0.57
    🌇
    0.54
     سرمایہ
    0.53
     capitalismo
    0.53
    觎
    0.50
     പോലെ
    0.50
     działal
    0.50
    の世界
    0.49
     dunia
    0.49
     someday
    0.48
    Activations Density 0.001%

    No Known Activations