© 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. 609
    Prev
    Next
    INDEX
    Explanations

    relating to

    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
     conférence
    -1.10
    izarse
    -0.94
     épreuve
    -0.90
     üzerinden
    -0.89
     địch
    -0.88
     eredmény
    -0.86
     placas
    -0.84
     componentes
    -0.82
     combinaison
    -0.82
    calciatore
    -0.82
    POSITIVE LOGITS
     specifically
    1.78
    specifically
    1.68
     Specifically
    1.44
    Specifically
    1.41
     relate
    1.30
     específicamente
    1.27
     relates
    1.23
    SPECIFIC
    1.22
     directly
    1.21
     related
    1.20
    Activations Density 0.109%

    No Known Activations