© 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. 16-GEMMASCOPE-2-RES-262K
    7. 107473
    Prev
    Next
    INDEX
    Explanations

    milk semen

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ན
    0.54
     n
    0.53
    ли
    0.51
    も
    0.50
     chọn
    0.47
    スマートフォン
    0.46
    เลือก
    0.45
     கூறினார்
    0.45
    となって
    0.44
    を経
    0.44
    POSITIVE LOGITS
    etition
    0.52
    swith
    0.48
    သမ
    0.48
    refreshToken
    0.47
     हैज
    0.47
    cknow
    0.47
     zasad
    0.47
    otov
    0.46
     출
    0.46
     Butch
    0.46
    Activations Density 0.000%

    No Known Activations