© 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. 6670
    Prev
    Next
    INDEX
    Explanations

    personal vs. other pronouns

    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
    eeq
    2.17
    н
    2.12
    ब्ल्यू
    2.02
    ライン
    1.98
     “[
    1.97
     رکھے
    1.96
    til
    1.94
     부
    1.94
     kuy
    1.94
    رک
    1.93
    POSITIVE LOGITS
     Desmond
    2.17
     Ansel
    2.10
    ండి
    2.07
    ણ
    2.06
    ిన
    2.05
    老大
    2.03
    вис
    1.99
     प्रोटे
    1.98
     त्यात
    1.94
    AAD
    1.93
    Activations Density 0.872%

    No Known Activations