© 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. 34685
    Prev
    Next
    INDEX
    Explanations

    conversion process

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on uppercase technical identifiers, register names, acronyms, and numeric literals commonly found in code or hardware‐spec docs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    orters
    -0.75
    стоинства
    -0.71
     inspector
    -0.70
     Geister
    -0.69
    ugt
    -0.69
     Pantalla
    -0.69
    ால
    -0.68
     spolu
    -0.68
     cópia
    -0.65
    propag
    -0.65
    POSITIVE LOGITS
     conversion
    1.74
     conversions
    1.68
     Conversion
    1.62
    conversion
    1.56
    Conversion
    1.47
     converting
    1.38
     Conversions
    1.36
    conversions
    1.24
     Converting
    1.13
     converted
    1.13
    Activations Density 0.008%

    No Known Activations