© 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. 19073
    Prev
    Next
    INDEX
    Explanations

    than any other

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

    The neuron activates on the comparative phrase “any other,” flagging instances where something is being compared against all others.

    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
    "));
    -1.95
    ῞
    -1.72
     giapponese
    -1.65
    istungen
    -1.62
    "
    
    -1.61
    ").
    -1.59
    ",
    
    -1.57
    </h3>
    -1.56
    "));
    
    -1.56
    ")
    
    -1.55
    POSITIVE LOGITS
     of
    2.44
     like
    1.89
     we
    1.87
    vantaged
    1.84
     когда
    1.63
    _
    1.56
     when
    1.55
     what
    1.52
     manic
    1.52
     how
    1.51
    Activations Density 0.006%

    No Known Activations