© 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. 106648
    Prev
    Next
    INDEX
    Explanations

    WhatsApp and highway entities

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

    This neuron fires on capitalized, concatenated identifier tokens (e.g. CamelCase class or module names and other proper‐name tokens).

    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
     wouldn
    -0.73
    音频
    -0.71
     twitter
    -0.70
    ског
    -0.70
     Rø
    -0.70
    onCancel
    -0.69
     RELATIONS
    -0.68
     cognitive
    -0.68
    ressors
    -0.68
     did
    -0.68
    POSITIVE LOGITS
     WhatsApp
    0.98
    WhatsApp
    0.90
     Guiana
    0.85
    cemment
    0.84
    igroup
    0.83
    ຸ
    0.83
    chatId
    0.82
     WA
    0.82
    WA
    0.81
     Chats
    0.81
    Activations Density 0.013%

    No Known Activations