© 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. 92376
    Prev
    Next
    INDEX
    Explanations

    actions and entities

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

    The neuron primarily activates on numerical tokens—digits, numbers, and number‐related symbols—in the text.

    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
     HYDRA
    -1.02
    *}$
    -0.98
     มา
    -0.95
     procede
    -0.91
     GAO
    -0.91
    擔心
    -0.90
    tocks
    -0.90
    秾
    -0.89
     Bela
    -0.89
     andre
    -0.89
    POSITIVE LOGITS
     everyone
    1.14
    كرة
    0.90
     everybody
    0.85
     tangible
    0.81
     both
    0.79
     ormai
    0.79
     fechar
    0.79
    aurora
    0.79
     mennes
    0.77
    Everyone
    0.77
    Activations Density 0.026%

    No Known Activations