© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9435
    Prev
    Next
    INDEX
    Explanations

    deletion, fighters, matrix, get

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

    The neuron flags references to concrete technical artifacts—especially filenames, file‐extensions, and other resource or property names in code or documentation.

    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
    ściej
    -0.78
     analyse
    -0.74
     sells
    -0.74
     analyze
    -0.72
     buys
    -0.72
     anyhow
    -0.71
     spends
    -0.71
    おき
    -0.71
     bowiem
    -0.71
     deduce
    -0.71
    POSITIVE LOGITS
     lans
    0.93
    Ļ
    0.91
    studi
    0.91
     trening
    0.89
    nées
    0.88
    Socks
    0.88
    inhas
    0.87
     kompak
    0.85
    _;
    0.85
    gway
    0.84
    Activations Density 0.564%

    No Known Activations