© 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. 92421
    Prev
    Next
    INDEX
    Explanations

    non-English words or symbols

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

    The neuron is activated by numeric tokens—sequences of digits representing integer constants.

    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
     this
    -1.19
     without
    -0.97
     at
    -0.96
     or
    -0.96
     from
    -0.95
     with
    -0.94
     has
    -0.91
     although
    -0.90
     most
    -0.90
     sehr
    -0.88
    POSITIVE LOGITS
    
    1.02
     secre
    0.94
    ində
    0.92
     เป
    0.91
     seksi
    0.90
    跟你
    0.90
     allgemein
    0.90
    Proces
    0.89
     horrid
    0.89
     désigner
    0.88
    Activations Density 0.001%

    No Known Activations