© 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. 118468
    Prev
    Next
    INDEX
    Explanations

    gallstones

    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
     syph
    0.61
    stdout
    0.60
    ϭ
    0.59
    ك
    0.57
     ছিল
    0.57
    ज
    0.56
     vegetal
    0.55
    ش
    0.55
    ๐
    0.55
    s
    0.55
    POSITIVE LOGITS
    ous
    0.57
    ↵
    0.55
    ucker
    0.51
    aded
    0.50
     Yankee
    0.49
    уна
    0.49
     Gale
    0.48
     not
    0.47
    ừa
    0.47
     always
    0.47
    Activations Density 0.001%

    No Known Activations