© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102868
    Prev
    Next
    INDEX
    Explanations

    casing cemented

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

    The neuron fires strongly on the technical term “casing,” especially in contexts discussing well or tubing casings.

    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
     parachoque
    -2.94
    橚
    -2.77
     イラストレーション
    -2.63
     dipinto
    -2.58
     広場
    -2.47
    遢
    -2.47
     piscinas
    -2.45
     間取り
    -2.41
     abbraccio
    -2.41
    靣
    -2.38
    POSITIVE LOGITS
    of
    2.56
    ."
    2.45
    してた
    2.38
    ){
    2.28
     notwendig
    2.25
    versaire
    2.22
           
    2.20
    )$
    2.17
    ↵↵
    2.16
    ])
    2.16
    Activations Density 0.003%

    No Known Activations