© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100033
    Prev
    Next
    INDEX
    Explanations

    places and categories

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

    The neuron activates on capitalized proper nouns or named entities (e.g. names of teams, people, places, organizations).

    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
    なんだろう
    -2.30
    予定です
    -2.22
    ところです
    -2.05
    なのかな
    -2.05
    なのでしょう
    -1.99
    様です
    -1.98
     that
    -1.86
    ところに
    -1.77
    為に
    -1.77
    なのだ
    -1.75
    POSITIVE LOGITS
    子は
    3.00
    子が
    2.67
    はかなり
    2.25
    子さん
    2.17
     پنجم
    2.16
    が
    2.05
    は
    2.03
     في
    2.03
    は約
    2.03
    がとても
    2.02
    Activations Density 0.105%

    No Known Activations