© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33308
    Prev
    Next
    INDEX
    Explanations

    technical questions with api references

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

    The neuron detects URL and network resource strings (e.g., domain names, schemes, ports, and paths).

    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
     Richland
    -0.83
     Государ
    -0.81
    Konst
    -0.77
     Pavel
    -0.76
     Trey
    -0.73
     literals
    -0.73
    ცი
    -0.73
     rosin
    -0.73
    Pavel
    -0.73
    TTL
    -0.73
    POSITIVE LOGITS
     extension
    0.75
    ilaire
    0.75
     extensions
    0.73
    rój
    0.73
     monoc
    0.72
     lösen
    0.72
     ماده
    0.72
    وح
    0.71
     Polak
    0.71
    onation
    0.71
    Activations Density 0.008%

    No Known Activations