© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184383
    Prev
    Next
    INDEX
    Explanations

    block representatives

    np_acts-logits-general · gemini-2.5-flash-lite

    health, being decommissioned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ดวง
    0.50
    ۲
    0.50
    ۔
    0.49
    دی
    0.48
     勺
    0.47
    .*\
    0.47
     impure
    0.47
    দিগের
    0.45
    elihat
    0.45
    ("#{
    0.45
    POSITIVE LOGITS
    ро
    0.54
    盜
    0.50
     неравен
    0.48
    шча
    0.47
    क्
    0.46
    कौन
    0.46
    ПА
    0.45
     ప్రభ
    0.45
    売り
    0.45
    во
    0.45
    Activations Density 0.001%

    No Known Activations