© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127651
    Prev
    Next
    INDEX
    Explanations

    financial abbreviations and acronyms

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

    The neuron is detecting uppercase abbreviations or acronyms (tokens composed of two or more capital letters).

    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
    鋮
    -3.05
    creenshot
    -2.70
    
    -2.69
     mouseY
    -2.67
    +")
    -2.63
    禤
    -2.58
    yarakat
    -2.58
    StoryboardSegue
    -2.55
    "]);
    
    -2.53
    μος
    -2.50
    POSITIVE LOGITS
    As
    2.67
    1
    2.47
     and
    2.39
    <
    2.31
            
    2.16
     Zwar
    2.13
    At
    2.11
    While
    2.09
    On
    2.08
    Because
    2.06
    Activations Density 0.273%

    No Known Activations