© 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. 89385
    Prev
    Next
    INDEX
    Explanations

    drugs and substances

    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
     что
    0.66
     ().
    0.63
     elastomers
    0.61
    וד
    0.58
    '.
    0.56
    ت
    0.55
    지만
    0.55
    perity
    0.54
    고
    0.54
    ib
    0.53
    POSITIVE LOGITS
    fadeIn
    0.59
     viene
    0.59
    цкий
    0.57
     Decedent
    0.55
    u
    0.55
     Ships
    0.55
     বাঙ্গালীদের
    0.53
     vengan
    0.53
    Ⴀ
    0.53
    ಧಾರವಾಡ
    0.52
    Activations Density 0.001%

    No Known Activations