© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48056
    Prev
    Next
    INDEX
    Explanations

    exploration and policy

    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
    rimer
    -0.74
    mnist
    -0.73
     monetary
    -0.73
    ╠
    -0.70
    ilera
    -0.70
     phụ
    -0.70
    enein
    -0.68
     yêu
    -0.68
    inflammatory
    -0.66
    Hf
    -0.66
    POSITIVE LOGITS
     exploration
    1.40
     policy
    1.35
    exploration
    1.28
     Exploration
    1.23
    Policy
    1.21
     Policy
    1.19
    explore
    1.18
     explore
    1.16
    policy
    1.14
    explor
    1.14
    Activations Density 0.011%

    No Known Activations