© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130136
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on phrasing around new transportation routes and service announcements (e.g. “brand new route,” departure/arrival details, schedules).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    travel information and schedules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     working
    -1.44
     Theologie
    -1.36
     Erziehung
    -1.35
     кнопки
    -1.32
    んだり
    -1.30
     about
    -1.30
     parques
    -1.28
     miseria
    -1.27
     Unterrichts
    -1.26
    では
    -1.25
    POSITIVE LOGITS
     siè
    1.55
    亵
    1.48
    ֶּ
    1.48
    节奏
    1.38
    姿势
    1.38
    决心
    1.37
     február
    1.36
    汙
    1.35
    来到了
    1.34
    έ
    1.34
    Activations Density 0.035%

    No Known Activations