© 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. 67061
    Prev
    Next
    INDEX
    Explanations

    full followed by summary, story, or review

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

    The main thing this neuron does is detect occurrences of the word “full.”

    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
     Перейти
    -1.63
    KommentareTeilen
    -1.55
     desempen
    -1.55
     außerord
    -1.50
     einzigen
    -1.48
    ご存知
    -1.45
     pondering
    -1.45
     pagado
    -1.43
    tuu
    -1.43
    </h1>
    -1.43
    POSITIVE LOGITS
    9
    2.00
    4
    1.99
    5
    1.94
    。
    1.90
    3
    1.80
    6
    1.77
    7
    1.65
     actrice
    1.62
    っていましたが
    1.61
    ᜀ
    1.59
    Activations Density 0.007%

    No Known Activations