© 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. 34-GEMMASCOPE-RES-131K
    7. 3266
    Prev
    Next
    INDEX
    Explanations

    xml and html tags

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

    The neuron is keyed to numeric tokens (digits/number strings) in 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_34/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
     Redis
    -0.79
    mistry
    -0.78
    ajari
    -0.76
     jego
    -0.76
     começa
    -0.76
    ideon
    -0.74
     Spacing
    -0.73
    menea
    -0.73
    ủng
    -0.73
     his
    -0.72
    POSITIVE LOGITS
    ச்
    0.87
     pensa
    0.84
     directives
    0.83
     Könige
    0.83
     reyes
    0.81
    Dipl
    0.80
    赓
    0.79
     Coronavirus
    0.77
     preventative
    0.77
     coronavirus
    0.76
    Activations Density 0.022%

    No Known Activations