© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 105573
    Prev
    Next
    INDEX
    Explanations

    viral infections

    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
    ینی
    0.64
    лини
    0.63
    Ⲛ
    0.60
     بیوی
    0.57
    น
    0.57
    Disagree
    0.57
    もら
    0.57
    𝚃
    0.56
    Ди
    0.55
    𝚕
    0.55
    POSITIVE LOGITS
     the
    0.59
    \
    0.58
    們
    0.57
     panier
    0.57
     ocorr
    0.56
     to
    0.55
     martingale
    0.55
     tathapi
    0.55
     o
    0.54
     Versailles
    0.54
    Activations Density 0.001%

    No Known Activations