© 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. 116762
    Prev
    Next
    INDEX
    Explanations

    Chand, Chad, Chond starters

    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
    につき
    -0.75
     Known
    -0.73
     chitar
    -0.72
    したいと思います
    -0.72
    所謂
    -0.71
     مناطق
    -0.69
     Movements
    -0.69
     organismos
    -0.68
    квар
    -0.68
     épocas
    -0.68
    POSITIVE LOGITS
     bib
    0.84
     poe
    0.81
     dna
    0.79
     eclipse
    0.78
     Sheila
    0.78
     Dispute
    0.77
    واقع
    0.77
     irrevocable
    0.76
    bib
    0.75
     indep
    0.75
    Activations Density 0.016%

    No Known Activations