© 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. 117988
    Prev
    Next
    INDEX
    Explanations

    prins, prinz, princip, prin, municip

    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
    versing
    -0.79
     Yuen
    -0.76
     Dunn
    -0.74
    degrees
    -0.73
     postes
    -0.71
    isierte
    -0.71
     Columns
    -0.70
     Publicado
    -0.70
     Cos
    -0.70
    vica
    -0.70
    POSITIVE LOGITS
     prin
    1.23
     Prin
    1.23
    Prin
    1.19
     Principle
    1.18
    prin
    1.09
     Princip
    1.09
    Princip
    1.05
     princip
    1.04
     PRINCIP
    1.04
    PRINCIP
    1.01
    Activations Density 0.016%

    No Known Activations