© 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. 10-GEMMASCOPE-RES-131K
    7. 19185
    Prev
    Next
    INDEX
    Explanations

    specific markets

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

    The neuron activates on occurrences of the word “space,” especially when it refers to an industry, domain, or field (e.g. “blockchain space,” “drug space,” “tactical space”).

    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
     when
    -2.02
     three
    -1.78
     When
    -1.76
     four
    -1.63
    When
    -1.59
     five
    -1.55
     six
    -1.55
     over
    -1.55
     from
    -1.54
     seven
    -1.54
    POSITIVE LOGITS
    </strong>
    1.74
     sooo
    1.67
    i
    1.65
     ARISING
    1.63
     terrific
    1.63
     soooo
    1.61
     dando
    1.55
     craz
    1.55
     bizarre
    1.48
     naïve
    1.48
    Activations Density 0.020%

    No Known Activations