© 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. 10-GEMMASCOPE-RES-131K
    7. 11669
    Prev
    Next
    INDEX
    Explanations

    LaTeX document preparation

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

    LaTeX document preambles, specifically the closing brace of `\documentclass` declarations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    -
    -1.73
    AutoresizingMask
    -1.69
    ).
    -1.47
    ，
    -1.38
    
    -1.35
    
    -1.34
     Keine
    -1.32
     sogenannte
    -1.31
    是被
    -1.31
     Viele
    -1.31
    POSITIVE LOGITS
     that
    2.25
     joyas
    1.98
     virtudes
    1.70
     this
    1.67
     vrst
    1.59
     a
    1.59
     prioridades
    1.58
    ampaikan
    1.55
     exposiciones
    1.55
     valoraciones
    1.53
    Activations Density 0.001%

    No Known Activations