© 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. 102556
    Prev
    Next
    INDEX
    Explanations

    online services and entities

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

    The neuron strongly activates on occurrences of the exact word “Online.”

    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
     animada
    -0.82
     consider
    -0.81
     end
    -0.78
     Endlich
    -0.76
    tesi
    -0.76
    อ
    -0.75
    袍
    -0.74
    ’
    -0.74
    Naked
    -0.73
    naked
    -0.72
    POSITIVE LOGITS
     Offline
    0.99
    offline
    0.98
    beria
    0.90
     Hemsworth
    0.87
    Offline
    0.87
    ível
    0.86
    Cé
    0.85
    时长
    0.85
    陝
    0.84
    넨
    0.84
    Activations Density 0.013%

    No Known Activations