© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70123
    Prev
    Next
    INDEX
    Explanations

    academic and technical terms

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

    The neuron never activates on any tokens—it’s essentially a dead neuron.

    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
     using
    -0.94
     supremely
    -0.89
     with
    -0.88
     expertly
    -0.88
     spurred
    -0.85
     should
    -0.84
     ostensibly
    -0.83
     隊
    -0.82
     indicate
    -0.82
     even
    -0.81
    POSITIVE LOGITS
    Michigan
    0.99
     Dinas
    0.98
    Detroit
    0.97
    odils
    0.95
     Feinde
    0.93
    chool
    0.93
     BEING
    0.88
     QUARTER
    0.88
     ContentValues
    0.88
    preise
    0.86
    Activations Density 0.000%

    No Known Activations