© 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. 103224
    Prev
    Next
    INDEX
    Explanations

    PHPUnit, Hamcrest, mock object

    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
     йо
    -0.82
    烷
    -0.80
    子さん
    -0.80
    ellas
    -0.79
    IGRATION
    -0.78
    żeń
    -0.78
    горь
    -0.75
    WireFormat
    -0.75
     menyerang
    -0.73
    !("{
    -0.73
    POSITIVE LOGITS
     Burch
    0.85
    ⋅
    0.83
     canh
    0.81
     nhóm
    0.81
     Jazz
    0.75
    ఁ
    0.75
     ⋅
    0.74
     immobilier
    0.73
     ngu
    0.73
     controversy
    0.73
    Activations Density 0.003%

    No Known Activations