© 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. 48334
    Prev
    Next
    INDEX
    Explanations

    product descriptions and testimonials

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

    The neuron fires on the triple‐dash “---” markers that delimit metadata front‐matter in a document.

    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
    greek
    -1.20
    僑
    -1.20
     methodical
    -1.14
     aici
    -1.12
    caric
    -1.12
    prada
    -1.09
     najwyżs
    -1.09
     więc
    -1.09
     vanskelig
    -1.08
    italian
    -1.07
    POSITIVE LOGITS
     cari
    1.12
     prosent
    1.10
    service
    1.09
     φ
    1.09
     discours
    1.07
     Φ
    1.04
     emm
    1.04
     itin
    1.03
    s
    1.02
     Guitars
    1.02
    Activations Density 0.000%

    No Known Activations