© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116389
    Prev
    Next
    INDEX
    Explanations

    question/answer prompts

    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
     ||=
    -0.75
    昔から
    -0.74
     Zähne
    -0.72
    窍
    -0.69
     chants
    -0.68
     levering
    -0.68
     petri
    -0.68
    一个个
    -0.66
     scarring
    -0.66
     DPM
    -0.66
    POSITIVE LOGITS
     quiz
    1.64
     Quiz
    1.55
    quiz
    1.48
    Quiz
    1.41
     questions
    1.32
     answer
    1.30
     question
    1.30
     answers
    1.16
    questions
    1.13
     Question
    1.10
    Activations Density 0.003%

    No Known Activations