© 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-262K
    7. 80300
    Prev
    Next
    INDEX
    Explanations

    most important

    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
    Negative Logits
    ං
    0.51
    oflu
    0.49
    ₀
    0.48
    adal
    0.48
    OT
    0.47
    OWN
    0.47
    eto
    0.46
    aneously
    0.46
    ଙ
    0.46
    Tact
    0.45
    POSITIVE LOGITS
    Здравствуйте
    0.48
    רת
    0.47
    循
    0.44
    Неза
    0.43
    하고
    0.43
     demonstrate
    0.42
    配信
    0.42
     verein
    0.42
    되었습니다
    0.42
     retrait
    0.41
    Activations Density 0.000%

    No Known Activations