© 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. 10-GEMMASCOPE-RES-131K
    7. 85219
    Prev
    Next
    INDEX
    Explanations

    read followed by more

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

    The neuron specializes in spotting “read more” style UI prompts and their accompanying numeric or call-to-action tokens (e.g. “Read,” “More,” view counts, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     When
    -2.05
     While
    -1.98
     {
    -1.98
    ),
    -1.97
    m
    -1.89
     Normally
    -1.88
     Whenever
    -1.84
     p
    -1.80
     größten
    -1.79
     Obviously
    -1.77
    POSITIVE LOGITS
     gruppe
    2.16
    ⚢
    1.95
     simpel
    1.95
     utro
    1.92
    錾
    1.91
    *),
    1.90
    涐
    1.87
    缑
    1.84
     houd
    1.84
     neder
    1.81
    Activations Density 0.018%

    No Known Activations