© 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. 10-GEMMASCOPE-RES-131K
    7. 65138
    Prev
    Next
    INDEX
    Explanations

    ile, ive, ito, or ite endings

    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_10/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
    C
    -3.45
    禤
    -3.08
    Ꮸ
    -2.95
    淠
    -2.83
    Of
    -2.81
    _{
    -2.78
     grijs
    -2.75
    晅
    -2.72
    卌
    -2.70
    屜
    -2.66
    POSITIVE LOGITS
     trabal
    2.64
    
    2.59
     diversos
    2.55
     lamenta
    2.53
     pretende
    2.44
     tinha
    2.42
     сним
    2.41
     recopila
    2.41
     queria
    2.39
    蓠
    2.39
    Activations Density 0.007%

    No Known Activations