© 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. 22-GEMMASCOPE-RES-131K
    7. 33850
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming notation

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

    This neuron detects Python-style dotted namespace or attribute references (e.g. tokens in “module.name” expressions).

    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
     Käufer
    -1.03
    ཥ
    -0.99
    撂
    -0.97
     Bài
    -0.96
     kérdés
    -0.95
     deinen
    -0.93
     unbelievably
    -0.93
     abandonné
    -0.92
     bát
    -0.92
     effray
    -0.92
    POSITIVE LOGITS
    wać
    1.18
     it
    0.96
    tallet
    0.92
    0
    0.91
    ávají
    0.91
    fordshire
    0.90
    )))))
    0.89
    )')
    0.89
     pengobatan
    0.88
    bali
    0.88
    Activations Density 0.102%

    No Known Activations