© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13903
    Prev
    Next
    INDEX
    Explanations

    as though

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

    This neuron specifically fires on occurrences of the word “though.”

    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
     was
    -2.38
    ⃙
    -2.17
    𐑂
    -2.06
     הוא
    -1.97
    She
    -1.96
    iſter
    -1.95
    ”。
    -1.92
     從
    -1.91
     není
    -1.89
    After
    -1.85
    POSITIVE LOGITS
    
    2.28
     juſt
    2.27
     he
    2.17
    攙
    2.17
    ?
    2.09
    ون
    2.06
    
    2.06
    𐄁
    2.00
     they
    1.95
     were
    1.95
    Activations Density 0.001%

    No Known Activations