© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15807
    Prev
    Next
    INDEX
    Explanations

    committees and organizations

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

    toenails

    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_16k_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
    ູນ
    0.54
    پ
    0.50
     ยาว
    0.50
     बरसा
    0.49
     sonar
    0.49
    ਰ
    0.49
     sonor
    0.48
    넛
    0.48
     chiq
    0.47
     educativos
    0.47
    POSITIVE LOGITS
     Changing
    0.50
    టకు
    0.45
     Committee
    0.44
    ThreadGroup
    0.41
     Organizations
    0.41
     Committees
    0.41
     وقف
    0.41
     committee
    0.40
     Serving
    0.39
    гает
    0.38
    Activations Density 0.013%

    No Known Activations