© 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. 92150
    Prev
    Next
    INDEX
    Explanations

    probability density distributions

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

    The neuron strongly activates on occurrences of the word “probability” (and related statistical terms like distributions, density, mass functions, etc.).

    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
     probability
    -1.09
     probable
    -0.99
     probab
    -0.92
     probabilities
    -0.88
    дые
    -0.85
    概率
    -0.84
    probable
    -0.82
    probability
    -0.81
     probablemente
    -0.78
     probabil
    -0.77
    POSITIVE LOGITS
     density
    2.02
    density
    1.70
     Density
    1.66
     distribution
    1.57
     DENSITY
    1.51
     densities
    1.45
    Density
    1.44
    密度
    1.43
    distribution
    1.27
     distributions
    1.24
    Activations Density 0.031%

    No Known Activations