© 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. 99410
    Prev
    Next
    INDEX
    Explanations

    Brunei, Allah

    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
    .”
    -1.63
     we
    -1.62
     because
    -1.58
    !”
    -1.45
     If
    -1.45
    ,”
    -1.45
     if
    -1.43
     It
    -1.41
     In
    -1.41
     From
    -1.40
    POSITIVE LOGITS
     ingenieros
    1.55
     whimsical
    1.55
    沨
    1.46
     praticamente
    1.43
     mobiliario
    1.41
    狨
    1.41
    edì
    1.40
     Alemania
    1.40
     dueños
    1.37
    более
    1.36
    Activations Density 0.005%

    No Known Activations