© 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. 70474
    Prev
    Next
    INDEX
    Explanations

    organization abbreviations

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

    The neuron fires strongly on uppercase letter sequences representing acronyms or initialisms.

    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
    :
    -1.87
    ,
    -1.80
     of
    -1.66
    ;
    -1.49
     for
    -1.48
    !
    -1.38
    .
    -1.20
    ....
    -1.20
     +
    -1.15
     furthering
    -1.15
    POSITIVE LOGITS
    /</
    1.45
     soms
    1.42
     MINUTES
    1.41
    ❣️
    1.41
    鹩
    1.39
    PasswordEncoder
    1.37
    WARDS
    1.34
    ^)
    1.34
     \\
    1.33
     toit
    1.33
    Activations Density 0.024%

    No Known Activations