© 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. 68278
    Prev
    Next
    INDEX
    Explanations

    Organizations and specific groups

    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
     azonban
    -1.88
     però
    -1.76
     kuitenkin
    -1.74
     however
    -1.70
     jednak
    -1.59
     and
    -1.58
     však
    -1.52
    прочем
    -1.49
    However
    -1.41
     echter
    -1.35
    POSITIVE LOGITS
     it
    2.33
     was
    2.08
     therein
    1.80
     will
    1.77
     have
    1.68
     is
    1.59
     can
    1.59
     are
    1.58
     would
    1.56
     accordingly
    1.56
    Activations Density 0.159%

    No Known Activations