© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66704
    Prev
    Next
    INDEX
    Explanations

    ADA and Ada variations

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

    The neuron specifically detects the three-letter acronym “ADA.”

    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
    🡺
    -2.75
    摭
    -2.53
     wundersch
    -2.47
     dando
    -2.44
    
    -2.42
    荅
    -2.39
     zwanzig
    -2.38
     sogen
    -2.38
    StoryboardSegue
    -2.36
     solch
    -2.36
    POSITIVE LOGITS
    there
    2.81
    There
    2.72
    When
    2.69
    {
    2.58
    We
    2.55
    Some
    2.48
    .
    2.48
    After
    2.47
    Unlike
    2.47
     Surprisingly
    2.44
    Activations Density 0.005%

    No Known Activations