© 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. 54504
    Prev
    Next
    INDEX
    Explanations

    skin cancer

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

    function parameter strings in programming code, particularly file paths and resource identifiers.

    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
     danach
    -0.88
     qualquer
    -0.84
    either
    -0.81
     entweder
    -0.81
    ти
    -0.80
     ત
    -0.76
     după
    -0.76
     Local
    -0.76
     Жи
    -0.75
    кон
    -0.74
    POSITIVE LOGITS
     or
    1.38
     technologie
    1.10
     if
    0.90
    assertNotNull
    0.90
     délicieux
    0.87
    ӏ
    0.85
    orElse
    0.83
     systemu
    0.83
    altura
    0.82
    uchtet
    0.82
    Activations Density 0.012%

    No Known Activations