© 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. 10-GEMMASCOPE-RES-131K
    7. 38891
    Prev
    Next
    INDEX
    Explanations

    racing and qualifying events

    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
    érape
    -1.42
     donde
    -1.33
    两个
    -1.27
     vuonna
    -1.26
    ագրություն
    -1.26
    鯔
    -1.25
     novembre
    -1.21
    ferences
    -1.21
    Donde
    -1.21
    我可以
    -1.20
    POSITIVE LOGITS
     time
    1.40
     präsentiert
    1.39
    筱
    1.16
    paccio
    1.12
     ―
    1.09
     accurate
    1.08
     grüne
    1.06
     ganzes
    1.06
     erstes
    1.02
    臘
    1.02
    Activations Density 0.017%

    No Known Activations