© 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. 22-GEMMASCOPE-RES-131K
    7. 36671
    Prev
    Next
    INDEX
    Explanations

    media actions and options

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

    The neuron fires on interface control labels and separators—things like “Play,” “Download,” “Email,” “Print,” “Share,” “Get,” “More,” “Twitter,” “Facebook,” and the “|” bars that appear in navigation/toolbars.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Paket
    -1.26
     Puis
    -1.23
     vokal
    -1.22
     menyen
    -1.21
     Président
    -1.21
     Atau
    -1.20
     antik
    -1.16
    lors
    -1.15
    сама
    -1.15
     Klik
    -1.14
    POSITIVE LOGITS
     slight
    1.23
     on
    1.11
    尔夫
    1.09
    立場
    1.04
     more
    1.01
    |}\
    1.01
     previous
    0.99
     otros
    0.98
    ........
    0.97
     siendo
    0.95
    Activations Density 0.034%

    No Known Activations