© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54302
    Prev
    Next
    INDEX
    Explanations

    hexadecimal character sequences

    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
     or
    -1.67
     in
    -1.42
     that
    -1.41
     well
    -1.39
     JUST
    -1.37
     lavish
    -1.31
     so
    -1.27
     exquisitely
    -1.27
     after
    -1.25
     through
    -1.25
    POSITIVE LOGITS
     Provides
    1.46
    mainly
    1.41
    generally
    1.41
    primarily
    1.38
    eight
    1.34
    actually
    1.34
    nearly
    1.33
    both
    1.32
     Lesen
    1.30
    almost
    1.28
    Activations Density 0.014%

    No Known Activations