© 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. 10-GEMMASCOPE-RES-131K
    4. 61050
    Prev
    Next
    INDEX
    Explanations

    what is

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

    The neuron is sensitive to connective and linking words—prepositions, conjunctions, and similar “glue” words (for, and, includes, when, etc.) that introduce or join phrases.

    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
     Họ
    -1.60
    Their
    -1.45
    Ekster
    -1.36
    釔
    -1.35
     of
    -1.34
    Mijn
    -1.33
     Their
    -1.31
     їх
    -1.27
    戻る
    -1.25
    もや
    -1.24
    POSITIVE LOGITS
     a
    1.95
     another
    1.74
     where
    1.40
     these
    1.27
    }]$
    1.26
     when
    1.22
     getSelected
    1.22
     his
    1.22
     one
    1.20
    ᴛ
    1.20
    Activations Density 0.361%

    No Known Activations