© 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. 45308
    Prev
    Next
    INDEX
    Explanations

    publications and analysis

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

    The neuron fires on the names of magazines, journals, websites, and other publication titles.

    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
     vorhandenen
    -1.26
    (*´
    -1.23
    (´
    -1.22
    â
    -1.20
     damaligen
    -1.18
     politischen
    -1.15
    gebühren
    -1.15
    (^^)
    -1.15
     people
    -1.14
     растение
    -1.13
    POSITIVE LOGITS
    </em>
    1.61
    </i>
    1.45
    </b>
    1.36
    "",
    1.32
    </h5>
    1.31
    </h2>
    1.31
    vägen
    1.18
     choć
    1.11
    线的
    1.11
     mohou
    1.09
    Activations Density 0.105%

    No Known Activations