© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63014
    Prev
    Next
    INDEX
    Explanations

    names starting with ste

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

    The neuron detects surname fragments (proper‐name tokens), i.e. parts of last names in people’s full names.

    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
     butcher
    -0.87
    umir
    -0.77
     девушек
    -0.75
     convey
    -0.75
     Durée
    -0.74
    決勝
    -0.74
    berte
    -0.73
     crustace
    -0.73
    rolled
    -0.71
    dealer
    -0.71
    POSITIVE LOGITS
     heti
    0.77
     トマト
    0.75
    productList
    0.74
    citet
    0.72
    contador
    0.71
    Olá
    0.71
    晚安
    0.70
    accordion
    0.70
    initialise
    0.70
     minimise
    0.69
    Activations Density 0.020%

    No Known Activations