© 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. 22-GEMMASCOPE-RES-131K
    7. 39887
    Prev
    Next
    INDEX
    Explanations

    inner div

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

    The neuron strongly activates on standalone numeric tokens (e.g. years, list indices, or other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     především
    -1.00
     Глу
    -0.96
     pokoju
    -0.94
    ｗｗ
    -0.94
    ∅
    -0.91
     връ
    -0.90
     třeba
    -0.90
     пръ
    -0.90
     лъ
    -0.89
    电池
    -0.89
    POSITIVE LOGITS
    ↵↵
    1.04
     accedere
    1.01
     will
    0.99
    azzjoni
    0.94
     используя
    0.93
    sal
    0.91
    Angebot
    0.89
    TRAD
    0.89
    Liefer
    0.87
     mempunyai
    0.85
    Activations Density 0.010%

    No Known Activations