© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47620
    Prev
    Next
    INDEX
    Explanations

    beyond the conventional

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    იღ
    0.42
    fordern
    0.42
    Brig
    0.41
    𒌉
    0.38
    нная
    0.37
    Atual
    0.37
     nhanh
    0.37
    ತ್ತ
    0.37
     ！
    0.37
    超出
    0.37
    POSITIVE LOGITS
     conventional
    0.50
     Expected
    0.47
     mainstream
    0.45
    behaved
    0.44
     rainbows
    0.43
     convencional
    0.42
     peaks
    0.42
     Conventional
    0.41
     ordinary
    0.40
    conventional
    0.40
    Activations Density 0.010%

    No Known Activations