© 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. 34-GEMMASCOPE-RES-131K
    7. 34772
    Prev
    Next
    INDEX
    Explanations

    godmother, godfather, Fairy Queen, fairy dust

    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_34/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
    Baseline
    -0.82
     Reunion
    -0.78
    baseline
    -0.78
     baseline
    -0.77
    自杀
    -0.76
     mimpi
    -0.74
    geometric
    -0.73
     blé
    -0.71
     PASSWORD
    -0.71
    diens
    -0.71
    POSITIVE LOGITS
     god
    4.47
     godfather
    3.83
    god
    3.53
     Godfather
    3.22
     God
    3.05
    God
    2.83
     GOD
    2.41
    GOD
    2.23
     sponsors
    2.02
     sponsor
    1.91
    Activations Density 0.020%

    No Known Activations