© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86216
    Prev
    Next
    INDEX
    Explanations

    moral/ethical concepts and beliefs

    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
    薷
    -2.42
    uttgart
    -2.38
    When
    -2.38
    很棒
    -2.36
    鉨
    -2.33
    where
    -2.31
    孥
    -2.25
    with
    -2.23
     και
    -2.20
    وازم
    -2.20
    POSITIVE LOGITS
    ↵
    3.64
    ↵↵
    3.27
     “
    3.06
     (“
    2.72
     “[
    2.45
     “(
    2.42
    ’.
    2.31
     (‘
    2.31
    却又
    2.28
    er
    2.23
    Activations Density 0.003%

    No Known Activations