© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198515
    Prev
    Next
    INDEX
    Explanations

    preset programs, critically acclaimed, maintenance scheduling

    np_acts-logits-general · gemini-2.5-flash-lite

    Xiao Liuren, networking hardware, #1, next to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.53
    បី
    0.52
    u
    0.50
     similar
    0.49
    ୁ
    0.49
    sa
    0.47
    ti
    0.45
    U
    0.44
    sm
    0.44
    similar
    0.43
    POSITIVE LOGITS
    𒉈
    0.57
    രാഷ്ട്ര
    0.48
    ظم
    0.47
    دهای
    0.47
     म्यूचुअल
    0.46
    خ
    0.46
     نیز
    0.46
    ریل
    0.45
    蒴
    0.45
     ပြော
    0.43
    Activations Density 0.001%

    No Known Activations