© 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. 139413
    Prev
    Next
    INDEX
    Explanations

    named entities followed by verbs

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

    career success or opportunity

    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
     \
    0.46
     ク
    0.45
     屋
    0.44
    ब्रा
    0.44
    の本
    0.44
     evaporates
    0.42
     ਕੁ
    0.41
     hydrocarbons
    0.41
     หน
    0.40
     તા
    0.40
    POSITIVE LOGITS
    నర్
    0.57
    ธ์
    0.51
    лом
    0.50
    泂
    0.48
    식
    0.47
    ௦
    0.46
    썹
    0.46
    ము
    0.45
     souhaitez
    0.45
     saranam
    0.45
    Activations Density 0.000%

    No Known Activations