© 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. 45488
    Prev
    Next
    INDEX
    Explanations

    license and court documents

    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
     cał
    -0.83
    antwoorde
    -0.79
     serviceName
    -0.77
     Stär
    -0.77
     isChecked
    -0.75
    çando
    -0.75
     隆
    -0.74
     September
    -0.72
    想起
    -0.71
     dipping
    -0.71
    POSITIVE LOGITS
    物を
    0.83
    ってみ
    0.79
    常规
    0.78
     Cian
    0.78
    Probably
    0.77
     Pera
    0.76
     résistant
    0.76
    勵
    0.75
     EDITORIAL
    0.74
     PRINCIPLES
    0.72
    Activations Density 0.001%

    No Known Activations