© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5499
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by relationships

    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
     winner
    0.91
     scoring
    0.91
     Hall
    0.89
     once
    0.87
     scores
    0.83
     -
    0.82
    -
    0.80
     scorers
    0.80
    scoring
    0.79
     physics
    0.78
    POSITIVE LOGITS
     여행
    1.33
    ﹍
    1.29
     공개
    1.28
     샘
    1.27
    INV
    1.26
    غيل
    1.24
    کروچ
    1.24
     용
    1.23
    LEMN
    1.22
     정리
    1.21
    Activations Density 0.143%

    No Known Activations