© 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. 65389
    Prev
    Next
    INDEX
    Explanations

    id="

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

    The neuron fires on the quoted values assigned to HTML tag attributes (e.g. the text inside the quotes after id=, class=, name=, onclick=, etc.).

    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
    nings
    -1.13
     вопрос
    -1.05
    むしろ
    -1.03
     ด้วย
    -0.95
     pomaga
    -0.94
     is
    -0.94
     большей
    -0.94
    impianto
    -0.88
    Wikipedia
    -0.88
    majority
    -0.86
    POSITIVE LOGITS
     called
    1.09
    aimeJ
    1.05
    zám
    0.96
     also
    0.96
    కి
    0.94
    𝑒
    0.93
    éndolo
    0.93
     kemudian
    0.91
     tiež
    0.91
     desconocido
    0.91
    Activations Density 0.008%

    No Known Activations