© 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. 41721
    Prev
    Next
    INDEX
    Explanations

    xml utf-8 header

    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
     afir
    -1.91
    ’
    -1.82
     has
    -1.79
     ‘
    -1.78
     får
    -1.77
    ÔNG
    -1.77
    "।
    -1.77
     carburant
    -1.73
    )’
    -1.70
    了一
    -1.67
    POSITIVE LOGITS
     remarkably
    2.30
     această
    2.17
    during
    2.16
     verschillende
    2.08
     length
    2.05
     sechs
    2.02
    事も
    1.95
    ここで
    1.93
     strikingly
    1.93
     każ
    1.91
    Activations Density 0.004%

    No Known Activations