© 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. 83189
    Prev
    Next
    INDEX
    Explanations

    interpret

    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
     wir
    -1.00
    所有人
    -0.98
     форм
    -0.96
     primeiro
    -0.95
    时间
    -0.94
    arem
    -0.94
    他们的
    -0.93
     reinforcements
    -0.92
     tinker
    -0.91
     pelea
    -0.91
    POSITIVE LOGITS
    锃
    1.11
     dvi
    1.06
     interpreted
    1.04
    odles
    1.01
    哔
    1.00
     kuh
    1.00
     kombi
    1.00
     zobac
    0.99
    賡
    0.98
     Interpre
    0.97
    Activations Density 0.017%

    No Known Activations