© 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. 58533
    Prev
    Next
    INDEX
    Explanations

    was born, began, started

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

    origins or beginnings

    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
    ➹
    0.47
     garnished
    0.46
    함으로써
    0.46
    𒈹
    0.46
    픔
    0.45
     ختم
    0.43
    จัก
    0.42
     तहे
    0.42
    懐
    0.42
    பாத
    0.42
    POSITIVE LOGITS
     started
    0.76
     began
    0.73
     born
    0.63
     começou
    0.63
     was
    0.62
     initially
    0.61
    最初
    0.59
     nasceu
    0.59
     originally
    0.58
     commenced
    0.58
    Activations Density 0.019%

    No Known Activations