© 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-16K
    7. 11889
    Prev
    Next
    INDEX
    Explanations

    providing benefits and solutions

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

    fostering positive outcomes

    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
     captivating
    0.64
    不仅
    0.62
    ⁤
    0.58
    澧
    0.57
     undeniably
    0.56
    ופ
    0.55
     reimag
    0.54
    不僅
    0.52
     अद्वितीय
    0.52
    <unused2169>
    0.52
    POSITIVE LOGITS
     abusing
    0.64
     hurts
    0.61
     abortions
    0.56
     monies
    0.55
     prostitutes
    0.55
    called
    0.54
     deaths
    0.54
     died
    0.52
     (
    0.52
     blames
    0.52
    Activations Density 0.001%

    No Known Activations