© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41021
    Prev
    Next
    INDEX
    Explanations

    phrases starting with down the

    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_10/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
    {
    -2.31
    .
    -2.19
     and
    -2.14
     {
    -2.09
    _
    -2.02
     など
    -1.91
    S
    -1.91
     is
    -1.88
    J
    -1.86
    峮
    -1.64
    POSITIVE LOGITS
     unsere
    2.08
    nitř
    2.03
    ︲
    2.02
    ,”
    1.88
     maioria
    1.87
     jsme
    1.85
    𝓒
    1.85
    鱨
    1.85
     calça
    1.83
     freaking
    1.82
    Activations Density 0.013%

    No Known Activations