© 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. 34-GEMMASCOPE-RES-131K
    7. 117905
    Prev
    Next
    INDEX
    Explanations

    names, questions, and medical terms

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

    technical terms related to databases, queries, and data structures.

    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_34/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
     catal
    -0.73
     werde
    -0.68
    EXC
    -0.67
     SX
    -0.67
     sre
    -0.67
     Haitian
    -0.66
     LIV
    -0.66
    拧
    -0.66
    createdBy
    -0.66
    Обе
    -0.66
    POSITIVE LOGITS
     job
    0.86
    сов
    0.84
    τός
    0.79
     מוע
    0.75
     travaux
    0.75
    rounding
    0.75
    рана
    0.73
    job
    0.73
     liquido
    0.73
     教育
    0.72
    Activations Density 0.008%

    No Known Activations