© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129187
    Prev
    Next
    INDEX
    Explanations

    URLs after ://

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

    This neuron detects URL patterns and domain name components (e.g., “://”, “www.”, “.com”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     that
    -1.59
     either
    -1.48
     disminución
    -1.43
    儘
    -1.43
     dezelfde
    -1.41
     municípios
    -1.41
     Können
    -1.40
     Pued
    -1.40
     movilidad
    -1.35
    mbgg
    -1.34
    POSITIVE LOGITS
    www
    1.88
    матика
    1.70
     menik
    1.59
    TagMode
    1.56
    circ
    1.53
     setCode
    1.48
    ons
    1.47
     brune
    1.45
     mengucap
    1.44
    http
    1.43
    Activations Density 0.052%

    No Known Activations