© 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. 12123
    Prev
    Next
    INDEX
    Explanations

    program exit and return

    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
     zero
    -1.21
    zero
    -1.05
    ZERO
    -1.02
     cero
    -1.02
     zeros
    -1.00
     zéro
    -0.94
    果汁
    -0.93
     Zero
    -0.90
    ędziesz
    -0.90
     zeroes
    -0.89
    POSITIVE LOGITS
     Mour
    0.80
    itação
    0.75
     one
    0.75
    Allocation
    0.73
     pinch
    0.73
    1
    0.72
    关键
    0.72
     Allocation
    0.71
     실패
    0.70
    kili
    0.70
    Activations Density 0.003%

    No Known Activations