© 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. 131284
    Prev
    Next
    INDEX
    Explanations

    you

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

    identifying specific follow-up words

    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
     кеңселер
    0.51
     বলিয়াই
    0.51
    汙
    0.48
     década
    0.47
    角落
    0.46
     десяти
    0.46
     सहानुभूति
    0.46
     কৃতজ্ঞ
    0.45
    蕙
    0.45
    TITLE
    0.43
    POSITIVE LOGITS
     یا
    0.49
     psychosis
    0.48
     modulated
    0.48
     sprayed
    0.47
     روی
    0.47
     killers
    0.46
     modulates
    0.45
    ()}>
    0.45
     runter
    0.45
    lung
    0.45
    Activations Density 0.001%

    No Known Activations