© 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. 33922
    Prev
    Next
    INDEX
    Explanations

    web development libraries

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

    This neuron detects tokens in external CDN URLs (e.g. “bootstrapcdn.com/…”) that reference hosted library files.

    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
     or
    -1.89
     that
    -1.84
     At
    -1.77
     this
    -1.76
     each
    -1.74
    0
    -1.73
    Is
    -1.71
    -
    -1.71
    },
    -1.66
     either
    -1.66
    POSITIVE LOGITS
    Bjs
    1.79
    เกง
    1.72
    🏹
    1.66
     炖
    1.65
    鮠
    1.63
    mädchen
    1.62
    
    1.60
     grotte
    1.59
    鳚
    1.59
    blumen
    1.58
    Activations Density 0.001%

    No Known Activations