© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93321
    Prev
    Next
    INDEX
    Explanations

    `each` and `map` followed by `do`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    秀
    -0.87
     bileklik
    -0.81
     Munich
    -0.80
     通信
    -0.78
    鑣
    -0.77
    рано
    -0.77
    actment
    -0.77
     Heidegger
    -0.76
    hamcrest
    -0.76
    ーキ
    -0.76
    POSITIVE LOGITS
     do
    1.72
     {
    1.13
    (&
    0.91
     its
    0.84
     &
    0.82
    {
    0.82
    do
    0.81
     följande
    0.79
     {
    0.77
    即可
    0.73
    Activations Density 0.015%

    No Known Activations