© 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. 45686
    Prev
    Next
    INDEX
    Explanations

    CRC checksums

    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
     urine
    -0.79
    یدا
    -0.77
    邳
    -0.77
     národ
    -0.72
    ющей
    -0.72
     cargas
    -0.71
     corrobor
    -0.70
    Nguyễn
    -0.69
    جاب
    -0.68
     fichas
    -0.68
    POSITIVE LOGITS
    pony
    0.98
     polynomials
    0.95
     CRC
    0.88
     polynomial
    0.85
     polyn
    0.85
    init
    0.83
     dron
    0.82
    xfer
    0.82
    strom
    0.79
    himura
    0.79
    Activations Density 0.005%

    No Known Activations