© 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. 81411
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    вид
    -0.94
    джи
    -0.86
    retch
    -0.85
    coma
    -0.84
    tembro
    -0.83
    conclusion
    -0.83
    Footnote
    -0.81
     rechte
    -0.81
     เป
    -0.80
    fokus
    -0.79
    POSITIVE LOGITS
     questions
    1.51
     answers
    1.32
     answer
    1.20
    答案
    1.11
     for
    1.05
    Questions
    1.04
     Directions
    1.02
     question
    1.02
    Directions
    0.99
     directions
    0.98
    Activations Density 0.005%

    No Known Activations