© 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. 128705
    Prev
    Next
    INDEX
    Explanations

    names, people, and places

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

    The neuron activates on isolated capitalized tokens—particularly names, acronyms, or other proper‐noun words.

    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
    ”
    -3.22
    ’
    -3.20
    ↵
    -3.11
    AL
    -3.11
    In
    -2.97
    As
    -2.89
    or
    -2.77
    </i>
    -2.73
    l
    -2.70
    with
    -2.67
    POSITIVE LOGITS
    迓
    2.92
    狃
    2.80
    珢
    2.73
     you
    2.73
     ſta
    2.70
    嚒
    2.70
    ⏑
    2.67
    쨩
    2.64
    ↵↵
    2.61
     atrak
    2.59
    Activations Density 0.032%

    No Known Activations