© 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. 34232
    Prev
    Next
    INDEX
    Explanations

    data-* attributes and section starters

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

    This neuron detects HTML attribute names that include hyphens (e.g. data-*, aria-*).

    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
     each
    -1.20
     broader
    -1.20
    などが
    -1.18
    それも
    -1.14
    necessary
    -1.13
    liege
    -1.10
    IDENTIFIED
    -1.10
    glise
    -1.08
    still
    -1.07
    過程
    -1.06
    POSITIVE LOGITS
    ándonos
    1.11
    ımıza
    1.07
    каун
    1.07
     arou
    1.05
     and
    1.03
    ajā
    1.03
    gigabyte
    1.00
    ウィキ
    1.00
     peluang
    0.98
    )})
    0.98
    Activations Density 0.001%

    No Known Activations