© 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. 6836
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS formatting

    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
    协助
    -0.96
     ESD
    -0.78
     Assist
    -0.78
    ilitate
    -0.77
    assisted
    -0.77
     Auxiliary
    -0.76
    ilit
    -0.74
     Functional
    -0.73
     Captions
    -0.72
    ivable
    -0.71
    POSITIVE LOGITS
    spans
    0.90
    SPAN
    0.86
     mathvariant
    0.79
     classes
    0.76
     SPAN
    0.76
     bricolage
    0.76
    applied
    0.75
     span
    0.75
    engaruhi
    0.75
    sieve
    0.74
    Activations Density 0.073%

    No Known Activations