© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12782
    Prev
    Next
    INDEX
    Explanations

    offering further explanation or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    jis
    1.58
    hig
    1.58
    lady
    1.57
    y
    1.56
    وغ
    1.53
    iop
    1.51
    egen
    1.49
    biet
    1.49
    ap
    1.42
    aaaa
    1.42
    POSITIVE LOGITS
     resultArray
    2.11
     صنعتی
    1.97
     照片
    1.72
     源
    1.69
     是
    1.69
     arrayOf
    1.68
     Portrait
    1.66
     图
    1.65
     intArray
    1.65
     사는
    1.64
    Activations Density 0.001%

    No Known Activations