© 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. 34-GEMMASCOPE-RES-131K
    7. 106896
    Prev
    Next
    INDEX
    Explanations

    Greensburg, greasemonkey, grease guns

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

    The neuron selectively activates on capitalized name fragments or tokens that are parts of proper nouns (people’s names, place names, or organization 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_34/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
     conceit
    -0.76
     perusal
    -0.75
     Installations
    -0.74
    ウエスト
    -0.71
     predicated
    -0.69
     epist
    -0.69
     Tides
    -0.69
     dédié
    -0.68
     repost
    -0.68
    Zachary
    -0.68
    POSITIVE LOGITS
     películas
    0.77
    pertise
    0.75
     increíble
    0.74
    hner
    0.72
    ûn
    0.71
    垠
    0.71
     japonica
    0.69
     יְ
    0.68
    ⌘
    0.68
     Bacon
    0.67
    Activations Density 0.035%

    No Known Activations