© 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. 123498
    Prev
    Next
    INDEX
    Explanations

    therm- related words

    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
     atendido
    -2.86
    
    -2.78
    婠
    -2.72
    炁
    -2.67
     localizado
    -2.63
    椛
    -2.61
    linawan
    -2.59
    阏
    -2.59
    蝽
    -2.59
    論
    -2.52
    POSITIVE LOGITS
    We
    4.38
    This
    3.95
    There
    3.94
    Now
    3.56
    Then
    3.48
    If
    3.45
    Since
    3.39
    When
    3.33
    They
    3.33
    9
    3.31
    Activations Density 0.007%

    No Known Activations