© 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. 22-GEMMASCOPE-RES-131K
    7. 64838
    Prev
    Next
    INDEX
    Explanations

    index, priority, z-index, or other labels followed by colon

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

    The neuron fires on occurrences of the CSS “z‐index” property (including its numeric values).

    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
     “(
    -1.06
     (‘
    -1.05
     precisión
    -1.00
     Such
    -0.97
     请求
    -0.97
     jednym
    -0.96
    扑
    -0.94
    .].
    -0.93
    Such
    -0.91
    stare
    -0.91
    POSITIVE LOGITS
    BigInteger
    1.16
    ́c
    1.15
    BigInt
    1.12
    spd
    1.06
    可爱的
    1.04
     kubwa
    1.02
     anaknya
    1.02
     dieťa
    1.02
     великолеп
    1.01
     inaweza
    1.01
    Activations Density 0.001%

    No Known Activations