© 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. 115535
    Prev
    Next
    INDEX
    Explanations

    buy rating sell view

    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
     prévoit
    -0.91
     eccl
    -0.90
     minum
    -0.87
     PRED
    -0.86
     bocas
    -0.86
     dzied
    -0.85
     tracci
    -0.85
    :“……”
    -0.85
    スマートフォン
    -0.84
    یه
    -0.84
    POSITIVE LOGITS
     Street
    1.16
     (~
    1.05
     ~
    0.98
     secular
    0.93
     peers
    0.92
     valuation
    0.91
     thesis
    0.91
     versus
    0.90
    Valuation
    0.89
     EPS
    0.89
    Activations Density 0.020%

    No Known Activations