© 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. 72443
    Prev
    Next
    INDEX
    Explanations

    css font sizes or code separators

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

    This neuron detects numeric CSS measurements (numbers paired with units like px, pt, %, em, 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
     who
    -1.43
     when
    -1.38
     its
    -1.26
     that
    -1.13
     will
    -1.12
     which
    -1.05
     get
    -1.05
     sportback
    -1.04
    双方
    -1.03
     to
    -1.02
    POSITIVE LOGITS
    küche
    1.27
    苙
    1.25
    Rha
    1.19
     CascadeType
    1.17
     Grüßen
    1.17
     hade
    1.16
    plers
    1.15
    wasn
    1.15
     остальные
    1.13
    투
    1.13
    Activations Density 0.000%

    No Known Activations