© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116758
    Prev
    Next
    INDEX
    Explanations

    text legal license conditions

    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
     meint
    -0.81
     even
    -0.74
     álbum
    -0.72
    🚮
    -0.72
    ‌است
    -0.70
     mignon
    -0.70
     mør
    -0.69
     esfuerzan
    -0.69
     both
    -0.68
     SSSR
    -0.67
    POSITIVE LOGITS
    typeorm
    1.02
     festivities
    0.87
     dreary
    0.87
    amazonaws
    0.84
    巴
    0.84
     Therefore
    0.83
    nsan
    0.81
     مناف
    0.81
     amazon
    0.80
    caf
    0.79
    Activations Density 0.003%

    No Known Activations