© 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. 588
    Prev
    Next
    INDEX
    Explanations

    conditional else statements

    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
    chinelo
    -1.11
    에서는
    -1.06
    ες
    -1.05
    脔
    -1.02
     zarówno
    -0.99
    rijven
    -0.98
     asiática
    -0.98
     deputado
    -0.98
     abſ
    -0.98
    <0x17>
    -0.97
    POSITIVE LOGITS
    ↵
    1.01
     when
    0.97
     before
    0.95
     during
    0.91
     one
    0.89
     with
    0.87
     so
    0.87
     utilize
    0.85
     within
    0.84
     ciascuno
    0.84
    Activations Density 0.001%

    No Known Activations