© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8627
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and biological enzymes

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

    sperm, testosterone, zinc

    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_40_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
     seamlessly
    0.48
    waveform
    0.46
    密集
    0.46
    业界
    0.45
    辄
    0.45
     unsurprisingly
    0.44
     proactively
    0.44
    ंक्शन
    0.44
    高端
    0.44
    ามารถ
    0.43
    POSITIVE LOGITS
     physico
    0.66
     Moringa
    0.56
     Udaipur
    0.54
     physicochemical
    0.54
     neem
    0.53
    
    0.53
     Karachi
    0.52
     Iraqi
    0.52
     phytochemical
    0.52
     scanty
    0.51
    Activations Density 0.165%

    No Known Activations