© 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. 43912
    Prev
    Next
    INDEX
    Explanations

    during the

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

    phrases starting with 'during'

    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
    ی
    0.79
     fluorescent
    0.75
    ৬
    0.74
    ล
    0.72
     kilometre
    0.71
    ের
    0.71
    ू
    0.70
    다
    0.70
    ৩
    0.70
     grammatical
    0.69
    POSITIVE LOGITS
    t
    1.02
    е
    0.91
    will
    0.87
    a
    0.86
    k
    0.77
    During
    0.73
    ten
    0.71
    f
    0.71
    ه
    0.71
    during
    0.70
    Activations Density 0.057%

    No Known Activations