© 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. 26476
    Prev
    Next
    INDEX
    Explanations

    code syntax punctuation

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

    This neuron spotlights inline CSS style attributes (e.g. the “style=” and “display:” bits in HTML/template code).

    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
     that
    -0.95
    άζ
    -0.91
     the
    -0.90
    𝚛
    -0.89
     what
    -0.88
     Bevölkerung
    -0.88
     discussions
    -0.85
     individuals
    -0.84
    aurais
    -0.84
     collaborations
    -0.84
    POSITIVE LOGITS
     shuddered
    1.12
     paramètres
    1.05
     після
    1.05
    anchors
    1.04
     hatal
    1.03
     déroule
    1.03
     suspendu
    1.03
     sellado
    1.02
     principaux
    0.99
    bno
    0.98
    Activations Density 0.003%

    No Known Activations