© 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. 71660
    Prev
    Next
    INDEX
    Explanations

    legal citations, state names, and instructions

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

    The neuron fires on words that occur at the start of major blocks—section or paragraph headings and the first word of numbered/listed entries.

    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
     that
    -2.03
     "..\..\
    -2.02
    if
    -1.90
    锱
    -1.76
    lably
    -1.68
     <=",
    -1.66
     geene
    -1.64
    UAWEI
    -1.63
     Dicapai
    -1.63
     planten
    -1.62
    POSITIVE LOGITS
    </h2>
    1.81
     sorprende
    1.66
     рассказывает
    1.63
     is
    1.58
     sostener
    1.51
     $^{
    1.51
        
    1.51
     murky
    1.50
     unangemess
    1.49
     comunicarse
    1.49
    Activations Density 0.043%

    No Known Activations