© 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. 75388
    Prev
    Next
    INDEX
    Explanations

    product or service names

    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
    ⸢
    -1.41
     FAMILY
    -1.40
    Þ
    -1.34
     feuilles
    -1.31
     TRAVEL
    -1.29
     carreaux
    -1.28
     exceedingly
    -1.23
     CLAIMS
    -1.23
     LEARNING
    -1.22
     huiles
    -1.22
    POSITIVE LOGITS
     =
    1.48
     doing
    1.42
     get
    1.38
    :
    1.36
     an
    1.35
     keep
    1.34
     getting
    1.33
     for
    1.31
     does
    1.31
     using
    1.29
    Activations Density 0.060%

    No Known Activations