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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53536
    Prev
    Next
    INDEX
    Explanations

    html start tags

    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_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
    ا
    0.79
    ang
    0.65
    ug
    0.65
    ab
    0.64
    la
    0.64
    ४
    0.64
    1
    0.63
    aw
    0.63
    li
    0.61
    که
    0.61
    POSITIVE LOGITS
     to
    0.68
    in
    0.66
    لي
    0.63
     も
    0.63
     not
    0.59
     in
    0.58
     lưng
    0.58
     եւ
    0.57
    с
    0.57
     と
    0.55
    Activations Density 0.033%

    No Known Activations