© 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. 83693
    Prev
    Next
    INDEX
    Explanations

    numbers or codes containing 6

    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
     particularly
    -1.00
    Surely
    -0.91
     told
    -0.87
    ி
    -0.85
     stayed
    -0.85
     never
    -0.84
    strtotime
    -0.84
     allowed
    -0.83
     poca
    -0.83
     now
    -0.81
    POSITIVE LOGITS
     Then
    0.94
     ulike
    0.90
     Beside
    0.90
     Luego
    0.89
    Бил
    0.88
    imba
    0.88
     consult
    0.87
     redacción
    0.86
     psicología
    0.86
     zaz
    0.86
    Activations Density 0.013%

    No Known Activations