© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20102
    Prev
    Next
    INDEX
    Explanations

    digital communication and technology

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

    The neuron fires on occurrences of the word “digital,” especially as a standalone technical term.

    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
    sandalia
    -2.78
    ↵↵
    -2.70
     decidedly
    -2.59
    感じた
    -2.58
     cheia
    -2.48
     I
    -2.48
     terrific
    -2.45
     mangled
    -2.44
     WHILE
    -2.44
     hahaha
    -2.36
    POSITIVE LOGITS
    $
    3.64
    Just
    3.11
    Following
    3.06
    With
    3.00
    After
    2.98
    One
    2.83
    Another
    2.83
    इटम
    2.83
    Still
    2.80
    目前的
    2.78
    Activations Density 0.012%

    No Known Activations