© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27298
    Prev
    Next
    INDEX
    Explanations

    time ordering

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

    The neuron detects the asterisk (*) tokens at the start of lines in block (doc) comments.

    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
    providedIn
    -1.20
     artesanato
    -1.16
    　「
    -1.12
    didSet
    -1.10
    嫆
    -1.09
    elsif
    -1.08
     еле
    -1.05
     или
    -1.05
     verzi
    -1.02
    ſſen
    -1.01
    POSITIVE LOGITS
     riun
    1.12
     gehouden
    1.08
    einem
    1.06
     gekozen
    1.06
     bağlantılar
    1.06
     pictureBox
    1.05
     nadat
    1.05
     genoemd
    1.02
    Kepala
    1.02
     naast
    0.99
    Activations Density 0.001%

    No Known Activations