© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52774
    Prev
    Next
    INDEX
    Explanations

    artist finds

    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
    Negative Logits
     குறிப்பாக
    0.46
     करणारे
    0.40
    ின்றனர்
    0.39
    乂
    0.39
     예를
    0.39
     emotionally
    0.38
     산
    0.38
     Nā
    0.38
    達
    0.38
    ļ
    0.38
    POSITIVE LOGITS
     renamed
    0.43
    ឈ្មោះ
    0.40
    locator
    0.40
    шке
    0.40
    ومو
    0.39
    laptop
    0.39
     siglas
    0.39
    实行
    0.38
     titulada
    0.38
    世界上
    0.37
    Activations Density 0.023%

    No Known Activations