© 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. 115968
    Prev
    Next
    INDEX
    Explanations

    Sterling, Stirling, Starling, silver

    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
     desorption
    -0.78
    ostí
    -0.75
    orei
    -0.75
    sorption
    -0.75
    ded
    -0.72
     Swarm
    -0.72
    sbericht
    -0.71
    TextAppearance
    -0.70
     lenti
    -0.69
     stencil
    -0.69
    POSITIVE LOGITS
     silver
    1.31
     Silver
    1.18
     zilver
    1.11
    Silver
    0.96
    silver
    0.85
     серебря
    0.85
     Sterling
    0.84
     SILVER
    0.81
    承诺
    0.80
    Mesmo
    0.79
    Activations Density 0.010%

    No Known Activations