© 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. 50286
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief and confusion

    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
    にしました
    -0.92
     জন্য
    -0.91
    にします
    -0.91
     għall
    -0.90
     mivel
    -0.87
    さぁ
    -0.87
    ᯾
    -0.87
    registrar
    -0.87
    
    -0.85
    peut
    -0.83
    POSITIVE LOGITS
     are
    1.83
     is
    1.27
     did
    1.04
     why
    0.96
     am
    0.95
     were
    0.93
     kind
    0.92
     ainda
    0.88
    is
    0.87
     people
    0.87
    Activations Density 0.007%

    No Known Activations