© 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. 22-GEMMASCOPE-RES-131K
    4. 28389
    Prev
    Next
    INDEX
    Explanations

    website and link navigation

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

    The neuron fires on tokens that are part of explicit web‐navigation instructions and URLs (e.g. “via,” “go,” “to,” “visit,” “www,” “login,” “website,” “registry”).

    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
    These
    -1.16
     these
    -1.13
    重要的
    -1.09
    包括
    -1.07
     banheiro
    -1.04
    ських
    -1.02
     __
    
    -1.02
     those
    -1.00
     xuống
    -0.98
     pequeno
    -0.98
    POSITIVE LOGITS
     or
    1.45
     from
    1.44
     nocy
    1.05
    скую
    1.04
     eller
    1.04
     milliard
    1.03
     externes
    1.02
    ẖ
    1.02
     quelcon
    1.01
     fön
    1.00
    Activations Density 0.032%

    No Known Activations