© 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. 22-GEMMASCOPE-RES-131K
    7. 98658
    Prev
    Next
    INDEX
    Explanations

    code definitions and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     even
    -1.08
     przeciw
    -0.94
    Here
    -0.94
    ↵↵
    -0.88
     Even
    -0.87
    ıldı
    -0.84
    In
    -0.83
     Berechnung
    -0.83
    ,
    -0.83
     With
    -0.82
    POSITIVE LOGITS
    banez
    1.11
     Inſ
    1.09
    asca
    1.05
     этой
    1.05
    llac
    1.04
     tyto
    1.01
     attes
    1.00
     perna
    0.98
    INGER
    0.96
    írez
    0.96
    Activations Density 0.007%

    No Known Activations