© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12648
    Prev
    Next
    INDEX
    Explanations

    Jenny and Hyundai

    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
    ᷆
    -3.05
     leaſt
    -2.59
     اگر
    -2.44
    魮
    -2.30
    ’
    -2.28
    鰾
    -2.25
    zando
    -2.20
    6
    -2.11
     Он
    -2.09
    我知道
    -2.06
    POSITIVE LOGITS
     he
    2.31
    ⚬
    2.30
     avec
    2.22
     acep
    2.20
    ICOLON
    2.14
     almacen
    2.06
     religiously
    2.05
    わか
    2.03
    {
    2.03
     ܙ
    2.02
    Activations Density 0.001%

    No Known Activations