© 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. 67578
    Prev
    Next
    INDEX
    Explanations

    hex and code separators

    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
     which
    -2.02
     after
    -1.94
     because
    -1.79
     their
    -1.77
     from
    -1.67
     despite
    -1.63
     ostensibly
    -1.61
     in
    -1.60
     if
    -1.59
     or
    -1.55
    POSITIVE LOGITS
     sooo
    1.62
     soooo
    1.54
     insanely
    1.49
     FIVE
    1.38
    gives
    1.38
     FOUR
    1.36
     mediocre
    1.35
     REALLY
    1.34
     flamboyant
    1.33
     ridiculously
    1.32
    Activations Density 0.001%

    No Known Activations