© 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. 61112
    Prev
    Next
    INDEX
    Explanations

    reach terminal velocity

    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
     tightening
    0.41
     collectively
    0.41
     époque
    0.39
    უშ
    0.38
    qu
    0.37
    媝
    0.37
    writing
    0.37
    squ
    0.36
     optimum
    0.36
     successively
    0.36
    POSITIVE LOGITS
    ть
    0.47
     içer
    0.47
     statistik
    0.46
    Вели
    0.46
     Еўропы
    0.46
     dangereux
    0.44
    _(
    0.43
     kesalahan
    0.43
    Однако
    0.43
    meme
    0.43
    Activations Density 0.001%

    No Known Activations