© 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. 118306
    Prev
    Next
    INDEX
    Explanations

    types of interviews

    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
     conversing
    -0.90
     chatted
    -0.88
     inquired
    -0.87
     conversation
    -0.85
     Gespräch
    -0.84
     Dialogue
    -0.84
     listening
    -0.81
     conversación
    -0.80
     asked
    -0.80
     talking
    -0.79
    POSITIVE LOGITS
     interviews
    1.25
    インタビュー
    1.00
     entrevistas
    0.96
     entrevista
    0.94
     interview
    0.90
     formal
    0.88
     an
    0.82
     sit
    0.78
     vores
    0.77
    ામ
    0.77
    Activations Density 0.034%

    No Known Activations