© 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. 108937
    Prev
    Next
    INDEX
    Explanations

    class manipulation and lists

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

    The neuron fires on occurrences of “class” or “classes” and related class‐manipulation API calls (e.g. classList, toggleClass, removeClass) 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
    ɵɵelementEnd
    -0.83
     creazione
    -0.79
     SOBRE
    -0.78
    OTROS
    -0.77
    иму
    -0.75
     toler
    -0.75
    hoda
    -0.74
    妪
    -0.74
    ङ्
    -0.73
    我也不
    -0.73
    POSITIVE LOGITS
    toggle
    1.06
    dient
    0.92
    contains
    0.91
    Доба
    0.90
    Contains
    0.90
    removed
    0.90
    Queen
    0.89
    Remove
    0.89
     toggle
    0.89
    zzá
    0.87
    Activations Density 0.001%

    No Known Activations