© 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. 2203
    Prev
    Next
    INDEX
    Explanations

    publication without approval

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

    The neuron spots bibliographic metadata in front‐matter—dates, edition statements, original publication notes, and similarly formatted header information.

    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
     despite
    -0.88
     penyakit
    -0.77
    isierte
    -0.76
    brak
    -0.74
     vlo
    -0.71
    tabBar
    -0.71
     so
    -0.71
    PDATE
    -0.70
     mesaj
    -0.70
    :^{
    -0.69
    POSITIVE LOGITS
    ปัญหา
    0.88
     behandeln
    0.81
     variedad
    0.80
     Masalah
    0.79
     danych
    0.78
     insisted
    0.76
     insistence
    0.75
     erklä
    0.75
    ituitary
    0.75
    PLAIN
    0.75
    Activations Density 0.008%

    No Known Activations