© 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. 34-GEMMASCOPE-RES-131K
    7. 93855
    Prev
    Next
    INDEX
    Explanations

    comment markers or separators

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

    The neuron is primarily triggered by numeric tokens (e.g. version numbers, years, numeric identifiers, and other standalone digit strings).

    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
     polícia
    -0.88
     palav
    -0.87
    ATEUR
    -0.86
     igreja
    -0.85
     descubrió
    -0.82
    achusetts
    -0.82
    *~*~
    -0.81
    atura
    -0.81
    nese
    -0.81
    zied
    -0.79
    POSITIVE LOGITS
    //
    1.28
     -,
    1.15
    =,
    1.09
    -,
    1.00
    -.
    0.94
     _,
    0.91
     -.
    0.89
     –,
    0.89
    =.
    0.82
    #
    0.80
    Activations Density 0.091%

    No Known Activations