© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116075
    Prev
    Next
    INDEX
    Explanations

    consonant letters, combinations, clusters

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

    The neuron strongly activates on numeric tokens (digit sequences representing counts or values).

    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
     Cardinal
    -0.87
     percent
    -0.81
    letter
    -0.78
     letter
    -0.78
     letters
    -0.74
     Cardinals
    -0.73
     vowels
    -0.72
     Systematic
    -0.72
    categorical
    -0.71
     shape
    -0.71
    POSITIVE LOGITS
    組合
    0.94
    Clusters
    0.82
    hydr
    0.81
    Snippet
    0.79
     clusters
    0.79
    chts
    0.77
    .],
    0.75
    ningss
    0.75
     cluster
    0.75
     combinations
    0.74
    Activations Density 0.017%

    No Known Activations