© 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. 103841
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

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

    The neuron is tracking how far into the document you are—that is, it acts as a running position or “depth” counter for each token.

    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
    看着他
    -0.92
    僕も
    -0.87
     "{{
    -0.82
    :“……”
    -0.80
     gelişti
    -0.80
     "!
    -0.78
    payers
    -0.78
    ialis
    -0.78
     sclero
    -0.78
    burton
    -0.77
    POSITIVE LOGITS
     blonde
    1.74
     older
    1.54
     blond
    1.50
     taller
    1.47
     brunette
    1.45
     younger
    1.34
     smaller
    1.21
    blonde
    1.15
     shorter
    1.13
     boy
    1.10
    Activations Density 0.008%

    No Known Activations