© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64452
    Prev
    Next
    INDEX
    Explanations

    moderate and controlled

    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
     constamment
    -0.90
     rapidement
    -0.88
     undivided
    -0.88
     automatisch
    -0.87
     unabhängig
    -0.87
     независи
    -0.86
    дѣ
    -0.85
    直接
    -0.85
     sürekli
    -0.84
     lada
    -0.83
    POSITIVE LOGITS
     reasonable
    2.27
     appropriate
    2.22
     moderate
    2.20
     carefully
    2.08
     controlled
    2.05
     harmless
    2.05
     appropriately
    1.95
     умер
    1.95
     moderately
    1.91
     occasional
    1.88
    Activations Density 0.098%

    No Known Activations