© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 87157
    Prev
    Next
    INDEX
    Explanations

    basketball dunks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    s
    0.87
    k
    0.75
    g
    0.72
    Mir
    0.69
    _
    0.68
    In
    0.67
    #
    0.66
    ال
    0.65
    1
    0.65
    EL
    0.64
    POSITIVE LOGITS
     sĩ
    0.69
     tolerant
    0.65
     сі
    0.63
     potência
    0.63
     posterior
    0.60
     verano
    0.60
     chirurg
    0.60
     verduras
    0.60
     dunk
    0.59
     comedor
    0.59
    Activations Density 0.001%

    No Known Activations