© 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. 47955
    Prev
    Next
    INDEX
    Explanations

    not going

    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
    о
    -0.92
    ไม่
    -0.91
    Cells
    -0.86
    {|
    -0.86
    Не
    -0.86
    お
    -0.86
    à
    -0.85
    hoo
    -0.84
    世界
    -0.84
    СКА
    -0.84
    POSITIVE LOGITS
     even
    1.65
     know
    1.45
     understand
    1.41
     deserve
    1.38
     understands
    1.33
     deserved
    1.28
     wanted
    1.26
     worth
    1.25
     liked
    1.24
     knew
    1.23
    Activations Density 0.057%

    No Known Activations