© 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. 117008
    Prev
    Next
    INDEX
    Explanations

    understanding of

    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
     blev
    -0.96
    Präsident
    -0.94
     känns
    -0.93
     plage
    -0.92
    Zubereitung
    -0.91
     سانتی
    -0.91
     potassium
    -0.91
     Vorm
    -0.90
     comiendo
    -0.90
    一块
    -0.89
    POSITIVE LOGITS
     of
    3.38
     understanding
    1.90
    understanding
    1.84
     Understanding
    1.67
     about
    1.63
    Understanding
    1.57
     понима
    1.55
     between
    1.50
     and
    1.48
     understand
    1.40
    Activations Density 0.014%

    No Known Activations