© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198544
    Prev
    Next
    INDEX
    Explanations

    Colorado Lamar CO

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

    email addresses and quantum mechanics

    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
     प्रभावशाली
    0.55
     средней
    0.52
     Тогда
    0.50
     출시
    0.50
    echolog
    0.50
     lançamento
    0.49
     🌱
    0.49
     स्तरीय
    0.48
    🏡
    0.47
    साल
    0.47
    POSITIVE LOGITS
     Methyl
    0.44
     trustee
    0.42
     Sudan
    0.41
     ointment
    0.41
     Trustees
    0.39
     ನಿಮಗೆ
    0.38
     Dobson
    0.38
     Trustee
    0.38
     lotion
    0.38
     كان
    0.38
    Activations Density 0.002%

    No Known Activations