© 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. 22-GEMMASCOPE-RES-131K
    4. 66007
    Prev
    Next
    INDEX
    Explanations

    as well

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

    The neuron fires strongly on the stock “may as well”/“might as well” idiom used to make a casual suggestion.

    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
     очень
    -1.13
     rất
    -1.07
    וּ
    -0.99
     today
    -0.97
    シブル
    -0.92
    可不是
    -0.91
     بسیار
    -0.90
     bardzo
    -0.90
    凄く
    -0.90
     similar
    -0.90
    POSITIVE LOGITS
     también
    1.35
     also
    1.27
    También
    1.09
     também
    1.07
    Also
    1.03
     també
    1.00
    unload
    0.97
    ֳ
    0.96
     {}
    
    0.96
    —"
    0.96
    Activations Density 0.020%

    No Known Activations