© 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. 1228
    Prev
    Next
    INDEX
    Explanations

    css selectors

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

    This neuron detects jQuery selector pseudo-class tokens (e.g. “:eq(…)”, “:contains(…)”, “:last”, etc.) in code.

    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
     voordat
    -0.85
     secure
    -0.85
    ғы
    -0.85
     deportivas
    -0.81
    ख़
    -0.80
     estrut
    -0.79
     igreja
    -0.77
     deudas
    -0.76
    Eyed
    -0.76
     tomada
    -0.75
    POSITIVE LOGITS
    ícil
    0.88
    hnen
    0.84
    habited
    0.82
    :+:
    0.81
    oauth
    0.80
    RATIO
    0.80
    ratio
    0.79
    Ski
    0.77
    }();
    0.77
    getLeft
    0.76
    Activations Density 0.080%

    No Known Activations