© 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. 118093
    Prev
    Next
    INDEX
    Explanations

    science fiction

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

    This neuron primarily detects numeric tokens (years, edition numbers, page counts, and other digits).

    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
    balleur
    -0.92
    毫米
    -0.88
     альбом
    -0.82
     funcionalidad
    -0.81
     мощность
    -0.81
    ällor
    -0.81
     ギフト
    -0.80
    getClassLoader
    -0.80
    HIB
    -0.79
    ını
    -0.77
    POSITIVE LOGITS
    Hein
    1.16
     SF
    1.16
     Hein
    1.13
     science
    1.11
    ansible
    1.05
    science
    1.03
    Locus
    0.97
     SCIENCE
    0.95
    SF
    0.94
     Locus
    0.94
    Activations Density 0.087%

    No Known Activations