© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37968
    Prev
    Next
    INDEX
    Explanations

    required designer variable

    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
     raiſ
    -0.89
     الفصل
    -0.86
     ſur
    -0.84
     pogod
    -0.82
     gorro
    -0.81
     倍
    -0.81
     grafic
    -0.80
    媗
    -0.80
     nós
    -0.80
     actores
    -0.79
    POSITIVE LOGITS
     method
    0.91
     Method
    0.88
     Required
    0.83
     designed
    0.82
    Method
    0.80
    METHOD
    0.79
     required
    0.79
       
    0.78
    upp
    0.77
     REQUIRED
    0.75
    Activations Density 0.001%

    No Known Activations