© 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. 93082
    Prev
    Next
    INDEX
    Explanations

    ionic and related framework components

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

    The neuron fires on references to the Ionic framework (tokens beginning with “ion-” or the word “ionic”).

    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
     plot
    -0.77
    staan
    -0.77
    Felt
    -0.72
    ねえ
    -0.69
     userRepository
    -0.68
    pozycji
    -0.68
    azza
    -0.67
    bral
    -0.67
    师兄
    -0.67
    Jaime
    -0.66
    POSITIVE LOGITS
    Ion
    0.87
     ルー
    0.85
     修
    0.81
     ICA
    0.79
    framework
    0.79
    ialak
    0.78
     Ion
    0.78
    Dist
    0.77
    Cord
    0.76
    ুন
    0.76
    Activations Density 0.010%

    No Known Activations