© 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. 1941
    Prev
    Next
    INDEX
    Explanations

    android, java, tencent, punctuation

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

    The neuron strongly activates on any token containing digits (numeric literals or numbers embedded in identifiers).

    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
     desmotiv
    -1.01
     isolada
    -1.00
    épar
    -0.96
     which
    -0.96
    Both
    -0.93
     where
    -0.93
     our
    -0.90
     löytyy
    -0.88
     with
    -0.88
    deceased
    -0.87
    POSITIVE LOGITS
    ;->
    1.39
    kawa
    0.97
    ………
    0.96
     Tencent
    0.96
     ρ
    0.96
    Ljava
    0.95
     andro
    0.94
     ($)
    0.94
     dosi
    0.94
     anx
    0.93
    Activations Density 0.001%

    No Known Activations