© 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. 9270
    Prev
    Next
    INDEX
    Explanations

    seismic design and structural irregularities

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

    exceeding or decoupling

    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
     rows
    0.47
     rownames
    0.46
     فات
    0.46
     ROWS
    0.45
     행
    0.44
     पंक्ति
    0.44
     filas
    0.43
     Hành
    0.42
     行
    0.41
    𒊕
    0.41
    POSITIVE LOGITS
     optimised
    0.44
     optimized
    0.41
     সবচে
    0.40
     সত্ব
    0.40
     decoupling
    0.39
    දි
    0.38
    Just
    0.37
    Supported
    0.37
     being
    0.37
     разрабаты
    0.37
    Activations Density 0.008%

    No Known Activations