© 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. 36009
    Prev
    Next
    INDEX
    Explanations

    dates, questions, and identifiers

    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
    Both
    -1.48
    Only
    -1.44
     perpetually
    -1.41
     venturing
    -1.35
     before
    -1.35
     unrelenting
    -1.34
     blatantly
    -1.33
     phenomenal
    -1.32
     without
    -1.30
     oftentimes
    -1.30
    POSITIVE LOGITS
     we
    1.72
     here
    1.56
    (“
    1.50
     trabalhadores
    1.47
    particularly
    1.46
     REALLY
    1.44
    wherein
    1.41
    earlier
    1.38
     you
    1.34
     najbardziej
    1.34
    Activations Density 0.000%

    No Known Activations