© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75613
    Prev
    Next
    INDEX
    Explanations

    outside of boundaries

    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
     plusieurs
    -1.12
     مختلف
    -1.11
     different
    -1.11
    不同的
    -1.09
    いろんな
    -1.05
     zowel
    -1.05
     seluruh
    -1.03
     både
    -1.02
    EVERY
    -1.02
    Westfalen
    -1.00
    POSITIVE LOGITS
     immediate
    2.50
     непосредственно
    1.87
    immediate
    1.83
     directly
    1.76
     immediately
    1.73
    直接
    1.70
     непосред
    1.70
     obvious
    1.57
     confines
    1.57
     immédi
    1.55
    Activations Density 0.086%

    No Known Activations