© 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. 22-GEMMASCOPE-RES-131K
    7. 15523
    Prev
    Next
    INDEX
    Explanations

    names followed by last names or verbs

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

    The neuron strongly activates on personal names (proper names of people).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     prépare
    -1.06
    already
    -1.03
    jecture
    -1.02
     großzü
    -1.00
     ACCIDENT
    -0.99
    我が家
    -0.97
     metoda
    -0.97
    Memento
    -0.97
    任何人
    -0.97
     angiography
    -0.96
    POSITIVE LOGITS
     of
    1.15
     ////
    1.02
    truction
    0.99
    ombe
    0.94
     Zeits
    0.93
    Ѕ
    0.91
    hadores
    0.90
    だか
    0.89
    cashire
    0.89
     and
    0.88
    Activations Density 0.011%

    No Known Activations