© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34498
    Prev
    Next
    INDEX
    Explanations

    field began, hold true, z or

    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
     terrific
    -1.91
     wondrous
    -1.69
     fantastic
    -1.66
     horrid
    -1.66
     sumptuous
    -1.62
     dreadful
    -1.57
     splendid
    -1.55
     crucial
    -1.55
     dismal
    -1.48
     superb
    -1.45
    POSITIVE LOGITS
     because
    2.17
     only
    1.79
     during
    1.68
     after
    1.67
     meticulously
    1.63
     although
    1.60
     undoubtedly
    1.45
     it
    1.42
     when
    1.41
     relatively
    1.41
    Activations Density 0.080%

    No Known Activations