© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94052
    Prev
    Next
    INDEX
    Explanations

    China Party advocating Western Values

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

    The neuron is chiefly detecting capitalized tokens—proper names, titles, and other words that begin with an uppercase letter.

    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
     pertenecen
    -0.91
    joystick
    -0.82
    Откры
    -0.81
     potvr
    -0.74
     régional
    -0.74
    UserList
    -0.74
    ונות
    -0.73
    ﻚ
    -0.73
    navi
    -0.71
    žiť
    -0.71
    POSITIVE LOGITS
     moral
    1.08
     ideological
    1.05
     campaign
    0.94
     Moral
    0.94
     Party
    0.86
    ideo
    0.85
    moral
    0.84
    Moral
    0.84
     morality
    0.83
     Ide
    0.82
    Activations Density 0.013%

    No Known Activations