© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 34207
    Prev
    Next
    INDEX
    Explanations

    .gitlab-ci.yml

    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
    Not in Any Lists

    No Comments

    Negative Logits
     dovoljno
    0.57
     announcement
    0.55
    ী
    0.54
     רא
    0.50
    科技
    0.49
     החד
    0.49
    orealistic
    0.48
     livestock
    0.48
     entirely
    0.48
    enziale
    0.48
    POSITIVE LOGITS
     Dijk
    0.65
     Reiki
    0.57
    करने
    0.56
     Пра
    0.55
    endam
    0.53
     Médico
    0.52
    醎
    0.52
    வார்கள்
    0.52
     শাজ
    0.52
    +(-
    0.52
    Activations Density 0.008%

    No Known Activations