© 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. 33028
    Prev
    Next
    INDEX
    Explanations

    Karnofsky scale

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

    This neuron detects proper names with specific endings or patterns, particularly focusing on surnames like "Karnofsky", "Karanjikar", and "Carnuba".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ...>
    -0.84
    tomime
    -0.81
     fractional
    -0.79
    Conclusión
    -0.77
     Ferrara
    -0.77
    agic
    -0.76
    asters
    -0.76
     فا
    -0.75
    Few
    -0.75
    gero
    -0.74
    POSITIVE LOGITS
    धार
    0.74
     INFORM
    0.69
     amongst
    0.69
    OPIN
    0.69
     Lifting
    0.69
     ambao
    0.68
     ouch
    0.68
     libération
    0.67
     času
    0.66
     Subsystem
    0.66
    Activations Density 0.028%

    No Known Activations