© 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. 75041
    Prev
    Next
    INDEX
    Explanations

    medical and scientific abbreviations

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

    document or file identifiers in scientific or technical publications.

    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
     PÅ
    -0.92
     télécharger
    -0.86
     TÉ
    -0.86
    ὄ
    -0.86
    の為
    -0.85
     Apesar
    -0.85
    quedas
    -0.84
     MÁ
    -0.84
    udis
    -0.84
    tecido
    -0.82
    POSITIVE LOGITS
    韮
    0.83
    が
    0.77
    bacter
    0.76
    uktion
    0.74
    などの
    0.73
    lief
    0.72
    そこは
    0.71
     вами
    0.71
     từ
    0.71
     there
    0.71
    Activations Density 0.000%

    No Known Activations