© 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. 124405
    Prev
    Next
    INDEX
    Explanations

    at someone

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

    to/at followed by pronoun/article

    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
     многи
    0.42
    icherweise
    0.42
     tutaj
    0.42
     populations
    0.40
     体
    0.40
    wati
    0.40
    ;');
    0.39
     आणि
    0.39
    ärm
    0.39
    ㅛ
    0.39
    POSITIVE LOGITS
     arkadaş
    0.48
    記者
    0.45
     prijatel
    0.45
     friend
    0.44
    记者
    0.44
     친구
    0.44
    เพื่อน
    0.43
     صدي
    0.43
     coworker
    0.42
     Trustee
    0.42
    Activations Density 0.058%

    No Known Activations