© 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. 89807
    Prev
    Next
    INDEX
    Explanations

    project configuration

    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
     plane
    -0.80
    Plane
    -0.79
     Planes
    -0.73
     Plane
    -0.73
     planes
    -0.71
     innymi
    -0.70
    жить
    -0.70
    Planes
    -0.69
    }}},
    -0.69
     stylized
    -0.69
    POSITIVE LOGITS
     Configuration
    1.72
    Configuration
    1.66
     configuration
    1.61
     configurations
    1.53
    configurations
    1.46
     Configurations
    1.39
    configuration
    1.36
     configs
    1.31
     configura
    1.30
    Configurations
    1.28
    Activations Density 0.052%

    No Known Activations