© 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. 80342
    Prev
    Next
    INDEX
    Explanations

    predictive domain analysis

    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
    Ска
    0.54
    /*
    0.51
     Idiot
    0.51
    Σ
    0.50
     Tori
    0.49
     ignor
    0.49
    Bollywood
    0.48
    傻
    0.47
    Sin
    0.47
     Scrap
    0.47
    POSITIVE LOGITS
    ava
    0.47
    AVA
    0.46
     nguồn
    0.43
     ሂደ
    0.43
     مواقع
    0.42
     tuyệt
    0.42
     نیرو
    0.42
    нняя
    0.42
    گی
    0.42
    étrique
    0.41
    Activations Density 0.000%

    No Known Activations