© 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. 34-GEMMASCOPE-RES-131K
    7. 78531
    Prev
    Next
    INDEX
    Explanations

    generic collections

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

    The neuron fires on occurrences of “Collection” or “Collections” identifiers (e.g. System.Collections.Generic).

    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
     く
    -0.88
    闖
    -0.84
    уса
    -0.84
     dividir
    -0.81
    gbaar
    -0.80
     nalazi
    -0.78
    CString
    -0.78
    斜
    -0.77
     chef
    -0.76
    து
    -0.76
    POSITIVE LOGITS
    Generic
    0.88
    generic
    0.81
    ỳnh
    0.79
     kanyang
    0.79
    理性
    0.77
    logrus
    0.76
    RECOMM
    0.75
    ‮
    0.75
    ches
    0.75
     wasser
    0.74
    Activations Density 0.003%

    No Known Activations