© 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. 68744
    Prev
    Next
    INDEX
    Explanations

    γ irradiation, nucleophile, Welcome, Twitter

    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
     this
    -1.63
     There
    -1.61
     and
    -1.60
     Most
    -1.59
     as
    -1.57
     may
    -1.54
     it
    -1.48
     Many
    -1.47
     Get
    -1.46
     from
    -1.45
    POSITIVE LOGITS
    providing
    1.77
    がありますが
    1.76
    很赞
    1.69
    Oby
    1.67
    もあって
    1.64
    
    1.63
    considering
    1.63
    苙
    1.62
    slightly
    1.59
    relatively
    1.56
    Activations Density 0.000%

    No Known Activations