© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150821
    Prev
    Next
    INDEX
    Explanations

    ethnic origin; materials and; gear icon

    np_acts-logits-general · gemini-2.5-flash-lite

    Church

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьте
    0.52
     ณ
    0.49
    Fog
    0.46
    кого
    0.46
    скага
    0.45
    ្វ
    0.44
     nke
    0.44
     шә
    0.44
    д
    0.44
    щего
    0.44
    POSITIVE LOGITS
     cruc
    0.50
     Church
    0.46
     CHURCH
    0.45
    コク
    0.45
     DETER
    0.42
     chu
    0.42
    はなく
    0.42
     Crown
    0.42
     Brownian
    0.42
     Cruc
    0.42
    Activations Density 0.000%

    No Known Activations