© 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. 34-GEMMASCOPE-RES-131K
    7. 1332
    Prev
    Next
    INDEX
    Explanations

    giving birth or rise

    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
    Give
    -1.12
     Give
    -1.03
     donner
    -0.96
     GIVE
    -0.95
     give
    -0.94
     Geben
    -0.90
    give
    -0.90
     giv
    -0.88
     giving
    -0.88
     oui
    -0.86
    POSITIVE LOGITS
     rise
    2.63
     birth
    2.05
     way
    1.91
    rise
    1.59
    Rise
    1.52
     Rise
    1.37
     arise
    1.29
     place
    1.29
     origin
    1.26
    birth
    1.25
    Activations Density 0.015%

    No Known Activations