© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195294
    Prev
    Next
    INDEX
    Explanations

    Eritrea and Eritrean

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

    attributes, reasons

    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
    oo
    0.54
    ő
    0.52
    ва
    0.50
     trakt
    0.48
     dir
    0.47
    ူ
    0.47
    inek
    0.46
    j
    0.46
     tm
    0.45
     plastica
    0.44
    POSITIVE LOGITS
     ਤੁਸੀਂ
    0.52
    ปฏิบัติ
    0.47
    ֮
    0.46
     ውጤ
    0.45
     Chore
    0.45
     hectare
    0.45
    თან
    0.43
    }}+\
    0.43
     ต่อ
    0.42
     Verhältnis
    0.42
    Activations Density 0.002%

    No Known Activations