© 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. 12832
    Prev
    Next
    INDEX
    Explanations

    XML tags and attributes

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

    The neuron fires on tokens that are XML/HTML attribute names (e.g. “Targets,” “aria‐valuenow,” “WantedBy”).

    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
    ),
    -1.68
     is
    -1.34
    )
    -1.32
     -
    -1.32
    ):
    -1.29
    ?
    -1.28
    a
    -1.27
    ).
    -1.26
    1
    -1.25
    ]
    -1.25
    POSITIVE LOGITS
    錞
    1.46
     lää
    1.42
    AÇÃO
    1.39
    sukienka
    1.34
    págs
    1.34
    gyű
    1.34
     mohl
    1.33
    rozum
    1.31
     gafas
    1.30
     häm
    1.29
    Activations Density 0.001%

    No Known Activations