© 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. 85945
    Prev
    Next
    INDEX
    Explanations

    coupon code, discounts, clearing

    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
    ⻬
    -2.64
    就
    -2.53
     attentive
    -2.38
     =
    -2.28
     就
    -2.25
     jednoduch
    -2.25
     coisas
    -2.22
    {
    -2.19
     alors
    -2.14
     endeavour
    -2.13
    POSITIVE LOGITS
    嫒
    2.52
    宬
    2.50
    捽
    2.41
    to
    2.38
    塒
    2.33
    羕
    2.31
    来自于
    2.28
     борьбе
    2.25
    筚
    2.23
    <i>
    2.20
    Activations Density 0.003%

    No Known Activations