© 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. 90466
    Prev
    Next
    INDEX
    Explanations

    followed by a sentence starter

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

    The main thing this neuron does is spot passages that present factual or technical information, often including explanations or numeric details.

    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
     prosent
    -1.05
     foarte
    -1.01
     isra
    -1.00
     confortable
    -0.98
    出的
    -0.97
     relig
    -0.96
     Başkanı
    -0.94
     kent
    -0.93
     '?'
    -0.93
     diagno
    -0.92
    POSITIVE LOGITS
     because
    1.49
     поскольку
    1.45
     Additionally
    1.45
     nevertheless
    1.40
     you
    1.38
     to
    1.37
     ponieważ
    1.33
     a
    1.30
    そのため
    1.30
     debido
    1.28
    Activations Density 0.005%

    No Known Activations