© 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. 10-GEMMASCOPE-RES-131K
    7. 41449
    Prev
    Next
    INDEX
    Explanations

    technical types or section titles

    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_10/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
    forKey
    -1.46
    tification
    -1.43
    latest
    -1.38
    required
    -1.37
     robuste
    -1.36
    fielder
    -1.34
    Offset
    -1.33
    fourths
    -1.33
     „
    -1.30
    necessary
    -1.30
    POSITIVE LOGITS
     who
    2.03
     would
    1.98
     when
    1.65
     knew
    1.63
     gave
    1.59
     still
    1.55
     should
    1.54
     could
    1.54
     before
    1.52
     usually
    1.52
    Activations Density 0.017%

    No Known Activations