© 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. 95610
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     every
    -2.27
     both
    -2.16
     with
    -2.16
     has
    -2.05
     each
    -1.98
     all
    -1.92
     this
    -1.92
     more
    -1.76
     as
    -1.73
     and
    -1.73
    POSITIVE LOGITS
     COULD
    1.86
     VERY
    1.80
     delightfully
    1.77
     ferocious
    1.73
     enraged
    1.72
     breathtaking
    1.71
    ඈ
    1.69
     exuber
    1.66
     astonishing
    1.65
     insanely
    1.63
    Activations Density 0.000%

    No Known Activations