© 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. 34-GEMMASCOPE-RES-131K
    7. 93331
    Prev
    Next
    INDEX
    Explanations

    DOM relationships

    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_34/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
     son
    -0.86
     Tochter
    -0.84
    Daughter
    -0.81
     SON
    -0.77
    ewel
    -0.76
     Sohn
    -0.74
    女兒
    -0.73
    daughter
    -0.72
     mera
    -0.71
     консуль
    -0.70
    POSITIVE LOGITS
     parent
    2.48
     parents
    2.03
     preceding
    1.98
    getParent
    1.88
    parent
    1.83
     next
    1.71
     adjacent
    1.64
     getParent
    1.64
    Parent
    1.63
     surrounding
    1.63
    Activations Density 0.021%

    No Known Activations