© 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. 40080
    Prev
    Next
    INDEX
    Explanations

    it all began

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

    This neuron detects the narrative‐opening idiom “It all …,” as in “It all started,” “It all begins,” “It all came about,” etc., that introduces how something happened.

    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
     of
    -2.98
    ;
    
    -2.06
    ⦊
    -1.88
     by
    -1.80
     and
    -1.78
    她的
    -1.77
     zealand
    -1.62
    檍
    -1.62
    )=>{
    
    -1.62
     что
    -1.61
    POSITIVE LOGITS
     It
    1.81
     caminha
    1.63
     révé
    1.60
    了起来
    1.59
     Things
    1.59
     People
    1.57
        
    1.54
    </strong>
    1.53
    闐
    1.52
     cultivate
    1.51
    Activations Density 0.005%

    No Known Activations