© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79941
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    text that appears in scientific or technical documents, particularly when discussing research or specifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively fires on numeric tokens or sequences (i.e. measurements, counts, IDs, and other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    nhung
    -1.05
     wundersch
    -1.05
     sufrido
    -1.01
    aust
    -1.00
     practices
    -0.98
     tráfico
    -0.98
    apic
    -0.97
     experimentado
    -0.97
     angene
    -0.96
     овощи
    -0.96
    POSITIVE LOGITS
    RA
    1.06
     répand
    1.02
    vieren
    1.02
    inescence
    1.01
    yet
    1.00
    corresponding
    0.99
     Instrum
    0.98
    N
    0.97
    only
    0.96
    then
    0.96
    Activations Density 0.110%

    No Known Activations