© 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. 22-GEMMASCOPE-RES-131K
    7. 9547
    Prev
    Next
    INDEX
    Explanations

    specific word following a common preposition

    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_22/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
     mittler
    -1.01
    撻
    -1.00
     brauch
    -0.94
     
    -0.93
     persön
    -0.93
     heuti
    -0.93
     gutem
    -0.92
     APPELLANT
    -0.91
     brauchst
    -0.91
    ranton
    -0.91
    POSITIVE LOGITS
    üns
    1.06
    当我
    1.01
    最近は
    0.99
    另一种
    0.98
    這邊
    0.96
    こちらは
    0.94
     När
    0.92
    geord
    0.91
    itando
    0.91
     sensib
    0.90
    Activations Density 0.074%

    No Known Activations