© 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. 15149
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

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

    The neuron strongly activates on the proper name “Max.”

    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
     parachoque
    -3.02
    訫
    -2.66
     ſame
    -2.58
    鑁
    -2.58
    篌
    -2.53
    .,"
    -2.48
    antaranya
    -2.45
     排骨
    -2.44
    龊
    -2.41
    ﻊ
    -2.38
    POSITIVE LOGITS
     −
    2.50
    Now
    2.38
    Who
    2.31
    </i>
    2.27
     –
    2.25
    That
    2.22
     et
    2.19
    What
    2.17
     กรัม
    2.14
     —
    2.13
    Activations Density 0.007%

    No Known Activations