© 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. 10-GEMMASCOPE-RES-131K
    4. 72779
    Prev
    Next
    INDEX
    Explanations

    Ashley followed by a surname

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

    This neuron activates on occurrences of the substring “ashley” in names or tokens.

    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
    on
    -2.95
    缡
    -2.89
     It
    -2.67
     使っ
    -2.66
     необходимость
    -2.58
    ,"
    -2.56
    borderSide
    -2.53
    }
    
    -2.44
    </strong>
    -2.42
     —
    -2.36
    POSITIVE LOGITS
    洐
    3.08
    珖
    3.05
    ᮣ
    3.00
     imaginative
    2.77
    羕
    2.75
    ).”
    2.73
    ࿆
    2.73
     groundbreaking
    2.69
    ?”
    2.64
    橚
    2.64
    Activations Density 0.001%

    No Known Activations