© 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. 84338
    Prev
    Next
    INDEX
    Explanations

    modifying context, timing, or state

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

    The neuron fires on words that sit immediately before a hard line‐break or segment boundary.

    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
     THEIR
    -1.13
     Their
    -1.10
     Its
    -1.02
     magnific
    -0.98
    Its
    -0.94
    向けの
    -0.93
    に入る
    -0.93
    ごとの
    -0.93
     dando
    -0.91
     recreated
    -0.90
    POSITIVE LOGITS
     one
    1.14
     ones
    1.12
    地區
    1.11
     it
    1.05
     them
    1.01
     more
    1.00
     people
    0.99
     situations
    0.94
     consideration
    0.93
     time
    0.93
    Activations Density 0.018%

    No Known Activations