© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6989
    Prev
    Next
    INDEX
    Explanations

    Pronouns like "They" and "Their"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     جهد
    1.08
     рубе
    1.06
    emergency
    1.04
    骤
    1.03
    creates
    1.01
     ниж
    1.00
    threshold
    0.99
    <unused2099>
    0.99
     военно
    0.99
     accelerates
    0.98
    POSITIVE LOGITS
     memakai
    0.96
     usage
    0.94
     pakai
    0.89
     Usage
    0.88
     practising
    0.87
     folos
    0.87
    活用
    0.85
    诠
    0.84
    解读
    0.84
     use
    0.84
    Activations Density 0.515%

    No Known Activations