© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65531
    Prev
    Next
    INDEX
    Explanations

    Nature and Science journal references

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

    scientific journal names like "Nature" and "Cell" when they appear in citations or references.

    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
     koneksi
    -1.30
    榈
    -1.24
     Duitse
    -1.22
     öde
    -1.22
    stantial
    -1.21
    elebr
    -1.18
     atau
    -1.18
     latihan
    -1.17
     öld
    -1.17
     pourra
    -1.16
    POSITIVE LOGITS
    </b>
    1.34
    رده
    1.19
     not
    1.12
    もありました
    1.11
     siir
    1.07
    Not
    1.02
    但这
    1.02
     Not
    1.02
     finds
    1.01
     休閒
    1.01
    Activations Density 0.002%

    No Known Activations