© 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. 75710
    Prev
    Next
    INDEX
    Explanations

    budget increases and funding

    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
    bildeten
    -0.93
     Alegre
    -0.88
    如今
    -0.87
     *++
    -0.85
     HttpNotFound
    -0.85
    cesso
    -0.84
    صدار
    -0.84
    ruck
    -0.81
    yle
    -0.79
     coord
    -0.79
    POSITIVE LOGITS
     additional
    1.27
     increase
    1.23
    เพิ่ม
    1.22
     추가
    1.16
     increased
    1.16
     funding
    1.14
    increase
    1.13
     beef
    1.12
     billions
    1.08
    increased
    1.08
    Activations Density 0.033%

    No Known Activations