© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11975
    Prev
    Next
    INDEX
    Explanations

    explanation of lists

    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_31_width_16k_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
    <unused2199>
    0.30
    τσι
    0.29
    이
    0.28
    ља
    0.28
    си
    0.27
    κτήθηκε
    0.27
    ст
    0.27
    <unused2125>
    0.27
    罍
    0.27
    гина
    0.26
    POSITIVE LOGITS
     (
    0.28
    layer
    0.27
     =
    0.26
     باستخدام
    0.25
    aturally
    0.25
     +
    0.24
    ibration
    0.24
     Boolean
    0.24
     Yes
    0.23
    ryption
    0.23
    Activations Density 0.563%

    No Known Activations