© 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. 22-GEMMASCOPE-RES-131K
    7. 35917
    Prev
    Next
    INDEX
    Explanations

    study aimed to investigate

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

    numbers and numerical data in academic or scientific text.

    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
     controversi
    -0.99
     Semantics
    -0.89
     RECRE
    -0.87
    bani
    -0.84
    ânsito
    -0.83
     JAMES
    -0.81
     Semen
    -0.79
     '-':
    -0.79
     активи
    -0.79
    uccess
    -0.79
    POSITIVE LOGITS
     mainly
    0.98
     fortsetter
    0.94
     because
    0.88
     also
    0.87
     principally
    0.87
     ايران
    0.87
     loses
    0.86
     people
    0.85
     those
    0.83
     this
    0.82
    Activations Density 0.002%

    No Known Activations