© 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. 100213
    Prev
    Next
    INDEX
    Explanations

    places and specific entities

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

    The neuron fires on capitalized named entities—proper nouns such as place names, organization or product names, and other named entities.

    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
    鲮
    -2.11
    frica
    -1.73
    amını
    -1.64
    峮
    -1.62
    batore
    -1.59
    íme
    -1.59
    噠
    -1.58
    ově
    -1.55
     were
    -1.53
    ercise
    -1.53
    POSITIVE LOGITS
    {
    1.91
    is
    1.73
    ma
    1.71
    _
    1.71
    To
    1.71
    not
    1.69
    łach
    1.63
    ik
    1.63
    ut
    1.59
     не
    1.57
    Activations Density 0.032%

    No Known Activations