© 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. 28562
    Prev
    Next
    INDEX
    Explanations

    updates and daily processes

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

    The neuron fires on numeric literals (integers and floats) in code.

    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
    ֻ
    -1.13
     [''],
    -1.05
    います
    -1.04
    ]--;
    -1.02
    amship
    -0.96
     būti
    -0.95
     ИЗ
    -0.93
    几天
    -0.92
    ံ
    -0.88
     дели
    -0.88
    POSITIVE LOGITS
     each
    1.11
     actualiza
    1.05
     every
    0.99
     frigo
    0.98
     update
    0.96
     daily
    0.96
     maille
    0.96
    ceased
    0.96
    tieth
    0.96
    更新
    0.96
    Activations Density 0.009%

    No Known Activations