© 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. 38205
    Prev
    Next
    INDEX
    Explanations

    phrases ending in prepositions

    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
     durante
    -1.13
    本日の
    -1.13
     umożliwia
    -1.10
     ngay
    -1.06
     organisiert
    -1.05
     again
    -1.04
     erneut
    -1.04
     μέσα
    -1.03
     direttamente
    -1.01
     хоте
    -1.01
    POSITIVE LOGITS
     in
    1.80
     on
    1.66
     at
    1.38
     \%,
    1.11
    €,
    1.05
    umą
    1.02
    ֑
    1.01
    kindness
    0.96
    meetings
    0.95
    ittää
    0.94
    Activations Density 0.271%

    No Known Activations