© 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. 131023
    Prev
    Next
    INDEX
    Explanations

    specific nouns and abbreviations

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

    This neuron is strongly triggered by the character sequence “cession” (as in procession, precession, 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
    銪
    -2.34
    鋨
    -2.30
     questionSearch
    -2.09
     pokoje
    -2.06
    獒
    -2.02
    Ꮉ
    -1.98
    envolvimento
    -1.95
          
    -1.95
    隳
    -1.92
    tku
    -1.91
    POSITIVE LOGITS
    '
    2.92
     "
    2.86
    ;
    
    2.55
     Then
    2.52
     стране
    2.41
     ""
    2.34
    尛
    2.30
    an
    2.19
    〠
    2.17
    自然的
    2.16
    Activations Density 0.005%

    No Known Activations