© 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. 10-GEMMASCOPE-RES-131K
    7. 75113
    Prev
    Next
    INDEX
    Explanations

    rough description

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

    The neuron detects occurrences of the root “rough” (e.g. “rough,” “Rough,” “roughness,” “roughened”) in words or phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    
    -2.06
     façade
    -2.03
     dieß
    -1.99
     británico
    -1.95
    ꦩ
    -1.88
    annya
    -1.83
    鲧
    -1.79
    鐗
    -1.77
    ㍑
    -1.75
     cansado
    -1.74
    POSITIVE LOGITS
    Rough
    2.16
     rough
    2.08
     et
    2.08
     Rough
    1.93
    0
    1.79
    個
    1.78
    再加上
    1.76
    3
    1.74
    次的
    1.70
    rough
    1.68
    Activations Density 0.010%

    No Known Activations