© 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. 22-GEMMASCOPE-RES-131K
    7. 35333
    Prev
    Next
    INDEX
    Explanations

    Marine Air Control Group

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

    This neuron detects the presence of English clitic markers—specifically apostrophe-based suffixes like ’s (possessive or contraction) and n’t (negation).

    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
     instinctively
    -1.05
    authier
    -0.97
     mouseY
    -0.96
    ==
    -0.93
     obstacles
    -0.92
    下面
    -0.92
    öd
    -0.90
    使用
    -0.88
    Lem
    -0.87
     it
    -0.85
    POSITIVE LOGITS
     répon
    1.05
    Rainer
    0.98
     caribou
    0.97
    Espa
    0.96
    Gost
    0.94
    AGRAM
    0.94
     complètes
    0.94
     VARIOUS
    0.93
     député
    0.91
    🚍
    0.91
    Activations Density 0.001%

    No Known Activations