© 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. 34-GEMMASCOPE-RES-131K
    7. 78479
    Prev
    Next
    INDEX
    Explanations

    well and position/extent modifiers

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

    The neuron specifically fires on the word “well” when it’s used as an intensifying adverb (e.g. “well-known,” “well over,” “well within,” etc.).

    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
    geth
    -1.00
    を
    -0.97
    معرفی
    -0.91
    期间
    -0.91
    紡
    -0.88
    دانلود
    -0.86
    <bos>
    -0.85
     referenties
    -0.84
     profesion
    -0.84
    しかも
    -0.84
    POSITIVE LOGITS
     into
    1.21
     beyond
    1.19
     before
    1.15
    為に
    1.13
     regarded
    1.08
     below
    1.01
    ようになって
    1.00
     well
    0.97
     ahead
    0.95
     outside
    0.95
    Activations Density 0.024%

    No Known Activations