© 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. 100710
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

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

    whitespace or indentation at the beginning of lines in code or formatted text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron chiefly fires on backslash characters (i.e. “\”) used in LaTeX or similar markup.

    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
    }
    -1.77
     posibil
    -1.62
    </strong>
    -1.59
    閙
    -1.59
    ]
    -1.56
     determina
    -1.54
     elétrico
    -1.53
    鹇
    -1.53
     должна
    -1.53
    --"
    -1.52
    POSITIVE LOGITS
     or
    1.83
    richtig
    1.79
    разви
    1.78
     zaten
    1.73
    meuble
    1.73
     adultes
    1.71
    groß
    1.71
     belki
    1.70
    쑹
    1.70
     например
    1.69
    Activations Density 0.003%

    No Known Activations