© 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. 81363
    Prev
    Next
    INDEX
    Explanations

    numbers preceding dimension

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

    This neuron activates on numeric dimension markers—e.g. “4D,” “five-dimensional,” “three-dimensional,” etc.—highlighting mentions of X-dimensional formats.

    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
    Биография
    -0.74
     terapia
    -0.72
    টি
    -0.69
    estars
    -0.66
     dovrebbe
    -0.65
    arky
    -0.65
    ▏
    -0.65
     ausp
    -0.64
     generative
    -0.64
    ày
    -0.63
    POSITIVE LOGITS
     dimensional
    2.23
    dimensional
    2.20
     dimension
    1.99
     Dimensional
    1.80
     dimensions
    1.79
    Dimensional
    1.73
     dimensionality
    1.73
    dimension
    1.72
     Dimension
    1.67
     dimensiones
    1.57
    Activations Density 0.042%

    No Known Activations