© 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. 39445
    Prev
    Next
    INDEX
    Explanations

    Medical Practitioners

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

    formatting or layout elements in documents, such as line breaks, headers, and special characters.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     when
    -0.82
    núť
    -0.79
     and
    -0.78
     metus
    -0.75
    icona
    -0.75
     مشارکت‌کنندگان
    -0.75
     նաև
    -0.75
    bucha
    -0.74
     OGSÅ
    -0.74
     tohto
    -0.74
    POSITIVE LOGITS
     cál
    0.97
     MÁ
    0.96
    铆
    0.92
    ᥲ
    0.92
    self
    0.92
     assiste
    0.91
     tré
    0.90
     COOK
    0.90
    orney
    0.90
     achat
    0.90
    Activations Density 0.013%

    No Known Activations