© 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. 10-GEMMASCOPE-RES-131K
    4. 80642
    Prev
    Next
    INDEX
    Explanations

    biophysics and dynamics simulations

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

    scientific research methodologies, particularly molecular dynamics simulations and other biophysical techniques.

    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_10/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
    few
    -1.32
    ing
    -1.31
    </h5>
    -1.30
     même
    -1.27
    時間で
    -1.26
    caf
    -1.24
     gleichen
    -1.23
     vraiment
    -1.22
     constructions
    -1.22
     few
    -1.20
    POSITIVE LOGITS
    María
    1.49
     nejlepší
    1.30
    ۹
    1.22
    Shu
    1.21
     μας
    1.19
     мл
    1.19
     løpet
    1.19
    áncer
    1.17
     ovation
    1.17
     supremely
    1.16
    Activations Density 0.079%

    No Known Activations