© 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. 10-GEMMASCOPE-RES-131K
    7. 112429
    Prev
    Next
    INDEX
    Explanations

    two-factor authentication, FR, Wrigley Field, cortisol, muscle

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

    scientific or technical terminology, especially chemical compounds, medical terms, and specialized nomenclature.

    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
     other
    -1.44
     would
    -1.38
     swojej
    -1.38
    kowania
    -1.35
     at
    -1.33
    
    -1.29
    𖤣
    -1.27
     dava
    -1.23
     vasi
    -1.23
     merusak
    -1.22
    POSITIVE LOGITS
    -
    1.42
    如何
    1.40
    ...
    1.40
    很多
    1.38
    两个
    1.35
    每
    1.34
    有些
    1.33
              
    1.33
    dekor
    1.30
    今年
    1.28
    Activations Density 0.211%

    No Known Activations