© 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. 34-GEMMASCOPE-RES-131K
    7. 892
    Prev
    Next
    INDEX
    Explanations

    puffing, swelling, inflated

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

    The neuron detects words related to swelling or inflation (e.g. “puff,” “puffed,” “puffing,” “inflated,” “deflated,” “inflatable”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    齡
    -0.83
     impresa
    -0.81
    even
    -0.80
     utente
    -0.79
    oc
    -0.78
     ؛
    -0.76
    렝
    -0.76
     Име
    -0.75
    desk
    -0.74
     chaînes
    -0.73
    POSITIVE LOGITS
    Puff
    1.32
     puff
    1.27
     Puff
    1.21
     pastry
    1.03
    利
    0.98
    πουργ
    0.90
    puff
    0.86
     swell
    0.85
    Huff
    0.85
    🐡
    0.84
    Activations Density 0.020%

    No Known Activations