© 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. 10-GEMMASCOPE-RES-131K
    7. 58722
    Prev
    Next
    INDEX
    Explanations

    URLs and paths

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

    This neuron detects parts of web URLs (domain names and path segments).

    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
     If
    -1.44
    </em>
    -1.43
     When
    -1.41
     häufigsten
    -1.38
     preparare
    -1.38
     砖
    -1.37
    accesso
    -1.36
     wesentlichen
    -1.33
    
    -1.30
    Prueba
    -1.29
    POSITIVE LOGITS
    الی
    1.48
    ‐
    1.47
    スポンサーリンク
    1.44
     nouvel
    1.38
    ми
    1.37
     herself
    1.35
    0
    1.33
    that
    1.31
    }
    1.30
     whom
    1.28
    Activations Density 0.047%

    No Known Activations