© 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. 10-GEMMASCOPE-RES-131K
    7. 73101
    Prev
    Next
    INDEX
    Explanations

    names of people

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

    The neuron fires on tokens that are personal proper names (first 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
    </h3>
    -1.58
     honom
    -1.48
    باشد
    -1.44
    aimeJ
    -1.42
    놋
    -1.41
    .
    -1.36
    鹮
    -1.36
    こだ
    -1.34
    éia
    -1.32
    扩张
    -1.32
    POSITIVE LOGITS
    ."
    1.77
    ubourg
    1.52
    :"
    1.48
     such
    1.47
     includes
    1.44
    　「
    1.40
    gernaut
    1.38
     this
    1.37
     illustrate
    1.37
     their
    1.35
    Activations Density 0.208%

    No Known Activations