© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3518
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    your, their, the

    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_53_width_65k_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
     असल्यास
    0.57
     NYC
    0.57
     इन्हे
    0.54
     $$$
    0.51
     אך
    0.51
     গ্রহন
    0.51
     మూవీ
    0.50
    大多
    0.49
     하며
    0.49
     “[
    0.48
    POSITIVE LOGITS
     그다음에
    1.12
     굉장히
    0.99
     ähm
    0.98
    比如说
    0.96
    っていう
    0.93
     sort
    0.86
     somebody
    0.86
    いろんな
    0.85
     oftentimes
    0.84
     everybody
    0.83
    Activations Density 0.584%

    No Known Activations