© 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. 99995
    Prev
    Next
    INDEX
    Explanations

    son of or daughter of

    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
     in
    -1.66
     máte
    -1.64
     других
    -1.56
    了他的
    -1.56
     інших
    -1.51
    atürk
    -1.50
    比特派
    -1.48
    EOUT
    -1.46
    祟
    -1.45
     iedereen
    -1.43
    POSITIVE LOGITS
     two
    1.78
     and
    1.71
     one
    1.67
    ’
    1.50
     краю
    1.45
     karte
    1.38
     melainkan
    1.38
     allAfrica
    1.38
     Ibidem
    1.37
     войск
    1.37
    Activations Density 0.007%

    No Known Activations