© 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. 2194
    Prev
    Next
    INDEX
    Explanations

    numbers and units like px

    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
     뒤
    0.21
     പ്രതീക്ഷ
    0.21
     गर्दन
    0.21
     Uptown
    0.21
     بیش
    0.20
     നേടിയ
    0.20
    สิ่งที่
    0.20
     ফলা
    0.20
     Congressman
    0.20
     Fitness
    0.19
    POSITIVE LOGITS
    ０
    0.25
    с
    0.25
    u
    0.24
     centena
    0.23
     ताकि
    0.23
     cientos
    0.23
    ри
    0.23
    0
    0.21
    a
    0.21
     cuyo
    0.21
    Activations Density 0.246%

    No Known Activations