© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5084
    Prev
    Next
    INDEX
    Explanations

    encountering people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    0.69
    Positions
    0.67
    घी
    0.65
    近平
    0.64
    밸
    0.62
     положении
    0.62
    ovanie
    0.61
    縝
    0.60
     정의역
    0.60
     बारी
    0.60
    POSITIVE LOGITS
     encountered
    1.47
     passers
    1.42
     encounter
    1.39
     encounters
    1.35
     pedestrians
    1.30
     Encounter
    1.27
     walking
    1.26
    encountered
    1.25
     passer
    1.24
     Begegn
    1.23
    Activations Density 0.151%

    No Known Activations