© 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-65K
    7. 2495
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specialists

    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_65k_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
    ↵
    0.81
    ل
    0.73
    ى
    0.72
    ون
    0.70
    er
    0.67
    的
    0.62
    2
    0.58
    b
    0.57
     For
    0.56
    ik
    0.55
    POSITIVE LOGITS
    <0x0D>
    0.63
     to
    0.59
     vítimas
    0.57
    s
    0.55
    Ը
    0.54
     válv
    0.54
     गाने
    0.53
     зоны
    0.53
     striées
    0.52
     especialistas
    0.52
    Activations Density 0.047%

    No Known Activations