© 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. 13549
    Prev
    Next
    INDEX
    Explanations

    array data structures

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

    programming arrays

    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
    ка
    0.83
    ン
    0.79
    কে
    0.77
    カ
    0.73
    Y
    0.72
    ന
    0.71
    ম
    0.68
    yı
    0.67
    ра
    0.67
     ecz
    0.67
    POSITIVE LOGITS
    j
    0.71
     Array
    0.67
     offens
    0.65
    阵
    0.63
    ై
    0.61
    言
    0.60
    下标
    0.59
    ే
    0.59
    ें
    0.58
    0.58
    Activations Density 0.002%

    No Known Activations