© 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. 11972
    Prev
    Next
    INDEX
    Explanations

    blink of an eye

    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
    semi
    -0.77
     reg
    -0.71
     животные
    -0.71
    menso
    -0.66
    bacillus
    -0.66
     cabinets
    -0.66
    ➖
    -0.66
     mixer
    -0.66
    UMNS
    -0.65
    isinstance
    -0.65
    POSITIVE LOGITS
    功夫
    1.13
     quarter
    1.03
     breaths
    0.88
     mãi
    0.86
     effort
    0.85
    呼吸
    0.85
     breathing
    0.83
     afternoon
    0.82
    差不多
    0.82
     tea
    0.80
    Activations Density 0.004%

    No Known Activations