© 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. 34-GEMMASCOPE-RES-131K
    4. 98333
    Prev
    Next
    INDEX
    Explanations

    fifth generation networks

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

    The neuron fires on mentions of mobile‐network generation labels (e.g. “5G network,” “4G,” “3G,” 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_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
    mados
    -0.80
    lorn
    -0.77
    rions
    -0.77
    čili
    -0.77
     семь
    -0.77
    ニラ
    -0.75
     zeven
    -0.75
     Wendell
    -0.75
    Wii
    -0.75
    ctypes
    -0.74
    POSITIVE LOGITS
    5
    1.59
     Fifth
    1.59
     fifth
    1.49
    Fifth
    1.38
     FIFTH
    1.18
     millimeter
    1.09
     пя
    1.09
    第五
    1.05
    5
    1.02
    fifth
    0.98
    Activations Density 0.028%

    No Known Activations