© 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. 87086
    Prev
    Next
    INDEX
    Explanations

    start or begin

    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
     rayures
    -1.59
     peinados
    -1.56
     nevera
    -1.55
    presents
    -1.49
    foundland
    -1.48
    swire
    -1.43
     مى
    -1.43
     tatuajes
    -1.43
     rése
    -1.42
    艄
    -1.42
    POSITIVE LOGITS
     to
    5.09
     be
    2.95
     get
    2.91
     make
    2.81
     provide
    2.50
     create
    2.45
     obtain
    2.41
     take
    2.39
     have
    2.30
     achieve
    2.30
    Activations Density 0.339%

    No Known Activations