© 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. 34-GEMMASCOPE-RES-131K
    7. 94055
    Prev
    Next
    INDEX
    Explanations

    independent division an engineer last thursday

    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_34/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
    ッズ
    -0.90
     Comput
    -0.87
     Computers
    -0.86
    ysz
    -0.81
     computer
    -0.79
    computer
    -0.77
    Cuen
    -0.77
    textnormal
    -0.76
     Computer
    -0.75
    ⊲
    -0.74
    POSITIVE LOGITS
    Pokud
    0.87
     dancer
    0.86
    inama
    0.85
     Epsom
    0.84
    公演
    0.82
     onstage
    0.82
    ₭
    0.79
    theater
    0.79
    issionais
    0.79
     Gebet
    0.77
    Activations Density 0.000%

    No Known Activations