© 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. 22-GEMMASCOPE-RES-131K
    7. 39951
    Prev
    Next
    INDEX
    Explanations

    closing brace or parenthesis

    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_22/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
     memili
    -1.06
     menetapkan
    -1.05
     mulai
    -1.02
     légitime
    -0.98
     effektiv
    -0.96
     menikmati
    -0.96
    vares
    -0.95
     delincuentes
    -0.94
     memperoleh
    -0.94
     melanjutkan
    -0.94
    POSITIVE LOGITS
     often
    1.01
    There
    0.90
     would
    0.90
    return
    0.88
    men
    0.88
    杜
    0.86
     Colle
    0.84
     particularly
    0.84
     Often
    0.84
    David
    0.82
    Activations Density 0.001%

    No Known Activations