© 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. 91033
    Prev
    Next
    INDEX
    Explanations

    legal citations or technical terms

    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
     Dě
    -0.91
     toprak
    -0.90
     selama
    -0.85
    Après
    -0.81
    损坏
    -0.80
     extinción
    -0.79
     their
    -0.79
    亩
    -0.78
    だね
    -0.77
     esquí
    -0.77
    POSITIVE LOGITS
     ویژگی
    0.87
     chirurg
    0.86
     Bij
    0.82
     wan
    0.81
     eat
    0.79
    ÖR
    0.79
    र्ड
    0.78
    Preserve
    0.78
     Preserve
    0.78
     ferme
    0.77
    Activations Density 0.006%

    No Known Activations