© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128643
    Prev
    Next
    INDEX
    Explanations

    somewhat like yellowish

    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
    澆
    -1.66
     for
    -1.61
    v
    -1.47
     from
    -1.44
     this
    -1.40
    j
    -1.40
     الموت
    -1.38
    for
    -1.32
    co
    -1.32
     and
    -1.31
    POSITIVE LOGITS
    火星
    1.80
    lblNewLabel
    1.63
    嫱
    1.55
     bVar
    1.52
     aDecoder
    1.50
     eléctrica
    1.46
    侂
    1.46
     发表于
    1.46
     ?>"
    1.45
     Empfindung
    1.45
    Activations Density 0.021%

    No Known Activations