© 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. 129013
    Prev
    Next
    INDEX
    Explanations

    training and being trained

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

    training your future

    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
    ים
    0.77
    '
    0.77
     is
    0.69
     présente
    0.67
    িং
    0.66
     adore
    0.65
    テック
    0.65
    ста
    0.64
    ിയ
    0.64
    ﺘ
    0.64
    POSITIVE LOGITS
     Trainings
    0.79
    训练
    0.74
    Training
    0.73
    დის
    0.72
    ā
    0.72
    x
    0.68
     تد
    0.64
    w
    0.63
    o
    0.63
    ched
    0.62
    Activations Density 0.104%

    No Known Activations