© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7861
    Prev
    Next
    INDEX
    Explanations

    oxygen delivery and use

    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
    ⟧
    0.89
    зей
    0.89
    LEGISLATIVE
    0.86
     Kall
    0.83
    UID
    0.82
    ள்ள
    0.82
    嵬
    0.81
    σει
    0.81
     aldosterone
    0.81
     hig
    0.81
    POSITIVE LOGITS
     Oxy
    1.22
     oxy
    1.18
     hypoxic
    1.18
     hypoxia
    1.13
    oxygen
    1.09
    oxygène
    1.09
    氧
    1.08
     oxygen
    1.05
    oxy
    1.03
     ऑक्सीजन
    1.02
    Activations Density 0.074%

    No Known Activations