© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5911
    Prev
    Next
    INDEX
    Explanations

    action toward someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     him
    1.42
     Him
    1.42
    +},
    1.06
    عون
    0.98
     thou
    0.96
     Ils
    0.95
     Ibid
    0.95
     hätten
    0.94
     未来
    0.94
    עים
    0.94
    POSITIVE LOGITS
     himself
    2.40
    妻子
    2.02
     swoim
    1.98
    麾
    1.96
     vợ
    1.90
     svoju
    1.89
     Himself
    1.87
     نفسه
    1.86
     his
    1.80
     istr
    1.79
    Activations Density 0.400%

    No Known Activations