© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98803
    Prev
    Next
    INDEX
    Explanations

    version or license

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

    This neuron detects CSS property declarations (e.g. “list-style:”, “padding:”, 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_34/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
    )}+
    -0.70
     chiều
    -0.69
    ridor
    -0.69
    Intelligent
    -0.69
     fasci
    -0.68
    Ề
    -0.68
    Chips
    -0.67
    nsk
    -0.67
    ulative
    -0.66
    療法
    -0.63
    POSITIVE LOGITS
    стка
    0.72
     Tok
    0.71
     舞
    0.66
     Syracuse
    0.66
     Assam
    0.65
    raged
    0.65
    TYPE
    0.64
    Tok
    0.64
    ování
    0.63
     الى
    0.63
    Activations Density 0.075%

    No Known Activations