© 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. 93892
    Prev
    Next
    INDEX
    Explanations

    disfavored except for

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

    The neuron mainly activates on the literal boolean value “false.”

    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
    Sqft
    -0.79
    uestran
    -0.78
    FAC
    -0.77
    dW
    -0.76
     Outsider
    -0.76
     egent
    -0.75
     his
    -0.74
    Ȧ
    -0.74
    面临
    -0.73
    DDT
    -0.73
    POSITIVE LOGITS
    cs
    0.88
     Tory
    0.84
    ↓
    0.84
     irá
    0.82
     diz
    0.76
     appare
    0.75
     花
    0.74
    agine
    0.74
    enqueue
    0.74
    que
    0.74
    Activations Density 0.001%

    No Known Activations