© 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. 34798
    Prev
    Next
    INDEX
    Explanations

    phrases continuing an action or state

    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
    как
    -0.94
     prosegu
    -0.89
     ventajas
    -0.88
     rychle
    -0.85
     Directorate
    -0.85
    しかし
    -0.84
    когда
    -0.83
    очень
    -0.83
     करे
    -0.82
    クリート
    -0.82
    POSITIVE LOGITS
     and
    1.14
     or
    0.97
    gears
    0.86
    uito
    0.82
     to
    0.79
    ajib
    0.79
     než
    0.79
     same
    0.75
    voet
    0.75
    quakes
    0.75
    Activations Density 0.012%

    No Known Activations