© 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. 22-GEMMASCOPE-RES-131K
    7. 92888
    Prev
    Next
    INDEX
    Explanations

    describing height

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

    The neuron fires almost exclusively on the word “tall” (in any casing), i.e. height descriptors using “tall.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    跄
    -2.39
    ↵↵
    -2.30
    salms
    -2.16
    ↵
    -2.16
     Berücksich
    -2.14
      
    -2.13
    峮
    -2.11
    莛
    -2.09
    
    -2.09
     potente
    -1.99
    POSITIVE LOGITS
    琑
    2.56
     uninterrupted
    2.28
     terlaris
    2.28
    𓋼
    2.23
    憮
    2.22
    鐿
    2.19
    jíma
    2.19
     alumínio
    2.11
    fatti
    2.11
    ://
    2.09
    Activations Density 0.005%

    No Known Activations