© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101521
    Prev
    Next
    INDEX
    Explanations

    compassion, empathy, remorse

    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
    蜮
    -2.89
    푏
    -2.86
    </strong>
    -2.72
     selben
    -2.70
    ※※
    -2.69
     Heilige
    -2.69
    肪
    -2.67
    ◆◆
    -2.63
    旆
    -2.59
     invitar
    -2.55
    POSITIVE LOGITS
    </td>
    3.53
    “
    3.20
    .
    3.11
    6
    2.78
    ↵↵
    2.58
    ↵
    2.58
    7
    2.56
    4
    2.52
    one
    2.50
    8
    2.50
    Activations Density 0.002%

    No Known Activations