© 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. 14488
    Prev
    Next
    INDEX
    Explanations

    unusual signs

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

    if condition

    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
     mede
    0.44
     traditionnelle
    0.42
    就會
    0.41
     سب
    0.40
    就会
    0.39
    兹
    0.39
     θα
    0.39
     tradicion
    0.39
    體
    0.38
     traditionnel
    0.38
    POSITIVE LOGITS
     suspiciously
    0.77
     signs
    0.70
     অস্বাভাবিক
    0.66
    Signs
    0.63
     suspicious
    0.63
     unusual
    0.61
    signs
    0.60
     असामान्य
    0.57
    明らかに
    0.57
     Signs
    0.56
    Activations Density 0.340%

    No Known Activations