© 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. 104446
    Prev
    Next
    INDEX
    Explanations

    abbreviations and introductory phrases

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

    The neuron is activated by numeric tokens (sequences of digits).

    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
     of
    -1.09
     However
    -0.94
    ↵↵
    -0.93
    奬
    -0.93
    _[
    -0.92
     =
    -0.91
     to
    -0.91
    DMF
    -0.90
     Fig
    -0.89
     Bangkok
    -0.88
    POSITIVE LOGITS
    atization
    1.15
    fillment
    1.07
    ੪
    1.05
    mereka
    1.04
     litio
    1.03
    izace
    1.03
    offered
    0.98
    tôi
    0.97
    áneamente
    0.97
     récompenses
    0.97
    Activations Density 0.000%

    No Known Activations