© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13073
    Prev
    Next
    INDEX
    Explanations

    surnames or first names of people

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

    The neuron mainly activates on multi‐token capitalized personal names (especially celebrity first and last 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_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
     they
    -1.55
     of
    -1.55
     there
    -1.40
     они
    -1.35
    i
    -1.34
    N
    -1.34
    they
    -1.32
     когда
    -1.32
     How
    -1.27
    Y
    -1.27
    POSITIVE LOGITS
    ⓒ
    1.52
    1.31
    ']
    1.31
    Happiness
    1.29
    ğu
    1.29
    "]
    1.27
     alfo
    1.26
    espejo
    1.25
    sibilidad
    1.23
     ftill
    1.23
    Activations Density 0.038%

    No Known Activations