© 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. 59021
    Prev
    Next
    INDEX
    Explanations

    at followed by time or limits

    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
    ╷
    -1.00
     également
    -0.96
     previos
    -0.94
    EDER
    -0.93
    WillAppear
    -0.93
    Evet
    -0.92
     امروز
    -0.87
    quels
    -0.85
    ᥉
    -0.84
    şa
    -0.84
    POSITIVE LOGITS
     once
    1.38
     first
    1.18
     precisely
    1.04
     about
    1.02
     Once
    1.02
     that
    1.02
     long
    0.95
     exactly
    0.94
     one
    0.93
     having
    0.92
    Activations Density 0.039%

    No Known Activations