© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128000
    Prev
    Next
    INDEX
    Explanations

    clinic pathological

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

    technical or specialized terminology, particularly in code, scientific, and medical contexts.

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

    The neuron highlights the single most content-bearing or unusually specific token in each snippet—typically the rare or specialized noun that carries the greatest information weight.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Pgina
    -2.14
    Добавлено
    -2.06
    ؍
    -1.88
    Struktur
    -1.85
    Cevap
    -1.82
    Ouverture
    -1.80
    Krank
    -1.80
     tacón
    -1.77
    Faktor
    -1.76
    Возраст
    -1.75
    POSITIVE LOGITS
     they
    2.59
     is
    2.42
     into
    2.36
     to
    2.30
    Aiheesta
    1.99
     It
    1.93
     on
    1.88
     most
    1.79
     was
    1.73
     
    1.70
    Activations Density 0.235%

    No Known Activations