© 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. 2232
    Prev
    Next
    INDEX
    Explanations

    URLs and identifiers

    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
     more
    -0.85
    зать
    -0.81
     think
    -0.80
     at
    -0.79
     half
    -0.77
     беже
    -0.76
     by
    -0.75
     fully
    -0.74
     white
    -0.72
     cannot
    -0.72
    POSITIVE LOGITS
    DRM
    0.88
    çs
    0.85
    Greatest
    0.84
     voren
    0.84
     erns
    0.84
    ALSO
    0.82
    ECE
    0.82
    GOAL
    0.80
     sinais
    0.80
     mêmes
    0.80
    Activations Density 0.006%

    No Known Activations