© 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. 56064
    Prev
    Next
    INDEX
    Explanations

    category detection

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

    This neuron never activates—it doesn’t detect any patterns and appears to be “dead.”

    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
    咳咳
    -1.22
     kics
    -1.05
    際には
    -0.96
    際の
    -0.93
    喏
    -0.92
    👸
    -0.90
    Tbh
    -0.88
    毗
    -0.88
    FWIW
    -0.86
     ree
    -0.85
    POSITIVE LOGITS
     Hello
    1.47
     Yeah
    1.46
     yeah
    1.41
    Hello
    1.40
     Hey
    1.38
    Yeah
    1.37
    Wow
    1.34
     Wow
    1.31
     Hi
    1.30
    Hi
    1.23
    Activations Density 0.202%

    No Known Activations