© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111231
    Prev
    Next
    INDEX
    Explanations

    total of numbers

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

    The neuron fires on numeric tokens (quantities, counts, percentages, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
            
    -2.16
     or
    -2.03
     if
    -1.98
     For
    -1.98
     of
    -1.86
    它
    -1.77
     on
    -1.75
           
    -1.75
     for
    -1.71
     This
    -1.71
    POSITIVE LOGITS
    コロナ禍
    1.84
     ſou
    1.81
    今後も
    1.78
     différents
    1.77
    ナイキ
    1.74
     juſ
    1.73
    その時
    1.71
    メルカリ
    1.71
    ユニクロ
    1.70
     accompagner
    1.70
    Activations Density 0.032%

    No Known Activations