© 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. 31-GEMMASCOPE-2-RES-262K
    7. 10985
    Prev
    Next
    INDEX
    Explanations

    describing transparency or translucence

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

    transparency and opacity

    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_262k_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
     крат
    0.55
     תק
    0.51
     사망
    0.50
    <unused2>
    0.49
     ITEMIZED
    0.48
    addAlignment
    0.48
     язы
    0.48
     경쟁
    0.48
     اجتما
    0.47
    <unused29>
    0.47
    POSITIVE LOGITS
     Transparent
    1.22
     Transparency
    1.17
     transparent
    1.16
     translucent
    1.10
     transparente
    1.08
    透明
    1.07
    transparent
    1.05
    Transparent
    1.05
     شفاف
    1.04
     прозра
    1.02
    Activations Density 0.036%

    No Known Activations