© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1067
    Prev
    Next
    INDEX
    Explanations

    blood clots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    溺
    0.92
    申込
    0.91
     εφαρ
    0.91
     ইউন
    0.88
     اقتص
    0.88
    ضح
    0.87
    巌
    0.87
     Tort
    0.86
    躊
    0.85
    格式
    0.85
    POSITIVE LOGITS
     cortisol
    1.35
     hormones
    1.29
     norepinephrine
    1.24
     levels
    1.22
     prostaglandins
    1.22
     Beta
    1.20
     progesterone
    1.18
     estrogen
    1.17
     upregulation
    1.17
     imbalance
    1.14
    Activations Density 1.066%

    No Known Activations