© 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. 66522
    Prev
    Next
    INDEX
    Explanations

    introduces specifics

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

    The neuron fires strongly on the CSS “border” token—especially in the “box-sizing: border-box” declarations.

    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
     its
    -1.16
     voulons
    -1.02
     todav
    -0.99
    或是
    -0.98
    それを
    -0.98
     hingga
    -0.98
     apartament
    -0.97
    示意图
    -0.97
     hata
    -0.94
    lyte
    -0.90
    POSITIVE LOGITS
     opět
    1.09
    accro
    1.06
    IVEN
    1.04
    んじゃ
    1.03
    痈
    1.01
    siehe
    1.00
    Hilsen
    1.00
     petróleo
    0.99
     vytvoř
    0.98
     errichtet
    0.96
    Activations Density 0.000%

    No Known Activations