© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73630
    Prev
    Next
    INDEX
    Explanations

    conversation with or about

    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
    ↵
    -1.59
    峮
    -1.40
     två
    -1.36
     salvaje
    -1.34
     antidesliz
    -1.33
     หรือ
    -1.30
     múltiple
    -1.30
     belga
    -1.27
    付属品
    -1.27
    搁
    -1.26
    POSITIVE LOGITS
     Then
    1.66
     After
    1.63
    繇
    1.55
     from
    1.48
    illai
    1.45
     Consequently
    1.45
     These
    1.41
     abrupt
    1.38
     They
    1.34
     Both
    1.33
    Activations Density 0.013%

    No Known Activations