© 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. 22-GEMMASCOPE-RES-131K
    7. 93070
    Prev
    Next
    INDEX
    Explanations

    HTML table headers or structure

    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_22/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
    alin
    -0.99
     vanligt
    -0.96
    dependent
    -0.96
     mengakui
    -0.90
    arroll
    -0.89
    了自己
    -0.88
     gênero
    -0.88
     Dependent
    -0.88
     aí
    -0.85
     Overall
    -0.85
    POSITIVE LOGITS
    情報は
    0.94
    intios
    0.89
     navigu
    0.86
    0.85
     homecoming
    0.85
    正确的
    0.84
    alitions
    0.82
    artamento
    0.82
    ättern
    0.82
     时尚
    0.81
    Activations Density 0.002%

    No Known Activations