© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44040
    Prev
    Next
    INDEX
    Explanations

    Dale followed by word

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

    The neuron fires on floating‐point numbers—that is, numeric tokens containing a decimal point.

    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
    -3.39
    3
    -3.17
     
    -3.17
     "
    -3.06
    ↵
    -2.92
    section
    -2.91
    e
    -2.88
    7
    -2.83
     '
    -2.83
     ...
    -2.69
    POSITIVE LOGITS
    銲
    3.09
    
    3.03
     墊
    2.89
    櫚
    2.83
    ᯾
    2.83
    铩
    2.81
    簟
    2.81
    ,’’
    2.77
     広場
    2.73
    
    2.69
    Activations Density 0.017%

    No Known Activations