© 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. 16-GEMMASCOPE-2-RES-16K
    7. 578
    Prev
    Next
    INDEX
    Explanations

    kills Listeria or bacteria

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

    abstract concepts and principles

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

    sentence continuation

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
    ر
    0.39
    ول
    0.33
    coefficients
    0.32
    以
    0.30
     είχε
    0.29
    وقال
    0.29
    ్ర
    0.29
    νας
    0.29
    وم
    0.29
    '_{
    0.29
    POSITIVE LOGITS
     ሁሉ
    0.29
     quality
    0.28
     typically
    0.28
     vivimos
    0.27
    ė
    0.27
     University
    0.26
     የመጀመሪያ
    0.26
     usually
    0.26
     worst
    0.26
    ę
    0.26
    Activations Density 0.000%

    No Known Activations