© 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. 83302
    Prev
    Next
    INDEX
    Explanations

    memoir and autobiography

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

    The neuron strongly activates on numeric tokens—especially year‐style digits—i.e. it’s detecting numbers (dates).

    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
     research
    -0.75
    Research
    -0.74
    ösungen
    -0.73
    データベース
    -0.73
     mengembangkan
    -0.72
     monitor
    -0.72
     database
    -0.71
     menciptakan
    -0.71
     databases
    -0.70
    教授
    -0.69
    POSITIVE LOGITS
     autobiography
    3.38
     memoir
    3.20
     memoirs
    3.00
     autobio
    2.56
     Autobiography
    2.41
     Memoirs
    2.34
     Memoir
    2.27
     memories
    2.13
    memo
    2.06
    Mem
    1.90
    Activations Density 0.048%

    No Known Activations