© 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. 10708
    Prev
    Next
    INDEX
    Explanations

    Jared followed by names

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

    The neuron is specially triggered by occurrences of the proper name “Jared.”

    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
    鉏
    -2.36
    ៚
    -2.27
    ⛥
    -2.22
     espoir
    -2.17
     tumble
    -2.17
    1
    -2.13
    \
    -2.11
     saker
    -2.08
     лиц
    -2.05
    「
    -2.05
    POSITIVE LOGITS
     shoved
    2.75
    </td>
    2.70
     of
    2.70
     peristiwa
    2.69
    ',
    2.61
     It
    2.55
     musuh
    2.50
     kebijakan
    2.48
     rencana
    2.44
    𖥧
    2.41
    Activations Density 0.006%

    No Known Activations