© 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. 91828
    Prev
    Next
    INDEX
    Explanations

    predominates or is dominant

    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
    olester
    -0.87
    elux
    -0.85
    closePath
    -0.81
    她也
    -0.81
    baguna
    -0.79
    nehå
    -0.78
    ilität
    -0.77
    мент
    -0.77
    icel
    -0.77
    íny
    -0.77
    POSITIVE LOGITS
     dominant
    5.25
     dominate
    4.91
     dominates
    4.78
    dominant
    4.63
     predominant
    4.38
     predominate
    4.28
     dominating
    4.28
     dominance
    4.09
    Domin
    4.09
    domin
    4.06
    Activations Density 0.230%

    No Known Activations