© 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. 28406
    Prev
    Next
    INDEX
    Explanations

    during a process

    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
    스터
    -0.83
     menegaskan
    -0.79
     favorit
    -0.78
    erder
    -0.77
    écran
    -0.77
    ⒏
    -0.76
     decisively
    -0.76
    íti
    -0.75
     Кубка
    -0.75
    can
    -0.74
    POSITIVE LOGITS
     until
    1.26
     while
    1.07
     durant
    1.05
     throughout
    1.00
    ahara
    0.98
    的过程中
    0.92
    משך
    0.91
    ագ
    0.87
    шёл
    0.86
     during
    0.85
    Activations Density 0.073%

    No Known Activations