© 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. 76224
    Prev
    Next
    INDEX
    Explanations

    attribute assignments or named parameters

    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
    #--
    -0.96
    myArray
    -0.88
     hoort
    -0.86
     future
    -0.84
     decidieron
    -0.84
    Стре
    -0.84
    を行いました
    -0.84
    梘
    -0.82
    خلص
    -0.80
    sanitized
    -0.80
    POSITIVE LOGITS
     "
    1.21
    disposing
    0.98
    ></
    0.95
    "></
    0.94
     name
    0.93
    ">
    0.92
     “
    0.92
     "_
    0.91
    ="
    0.90
     param
    0.86
    Activations Density 0.001%

    No Known Activations