© 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. 103333
    Prev
    Next
    INDEX
    Explanations

    documentation headers and notes

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

    The neuron fires on the opening of XML/HTML‐style tags (the “<” and tag names).

    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
     Leopard
    -0.78
    nextProps
    -0.67
    glBindBuffer
    -0.66
    ጃ
    -0.66
    newNode
    -0.65
    notation
    -0.64
    ListComponent
    -0.64
     continuous
    -0.64
    UNDEFINED
    -0.63
    𝗁
    -0.62
    POSITIVE LOGITS
     įsi
    0.76
     huella
    0.76
     phenol
    0.73
     谱
    0.68
    Sounds
    0.67
    谈
    0.67
     highlight
    0.67
    madas
    0.66
    _<
    0.65
    itor
    0.65
    Activations Density 0.076%

    No Known Activations