© 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. 60846
    Prev
    Next
    INDEX
    Explanations

    html tags

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

    The neuron fires on the start of XML/HTML closing tags (the “</” sequence).

    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
    .
    -3.16
    푣
    -2.97
    <td>
    -2.72
    )’
    -2.67
    ”,
    -2.64
    -2.58
    Maybe
    -2.52
    },
    -2.50
    N
    -2.42
    砗
    -2.42
    POSITIVE LOGITS
     are
    3.02
     alrededores
    2.98
     focuses
    2.75
     européens
    2.69
     proposent
    2.63
     входят
    2.61
     we
    2.53
     maternidade
    2.52
     muitos
    2.50
    他就
    2.50
    Activations Density 0.003%
    No Known Activations