© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3483
    Prev
    Next
    INDEX
    Explanations

    file paths and locations

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

    The neuron fires strongly on XML (or HTML-like) tag attribute names and related tokens (e.g. class, property, rect, x, location, schemaLocation).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    uttaa
    -0.85
     letteratura
    -0.81
     идей
    -0.80
    lojik
    -0.79
    apartment
    -0.76
    OPSIS
    -0.76
     pubblicato
    -0.76
     altera
    -0.75
     vettor
    -0.75
    tadora
    -0.75
    POSITIVE LOGITS
     filename
    0.93
     którzy
    0.81
    jum
    0.76
     protests
    0.75
     atunci
    0.75
     .)
    0.75
     파일
    0.75
    startY
    0.74
    Spacious
    0.74
    />
    0.72
    Activations Density 0.001%

    No Known Activations