© 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. 94245
    Prev
    Next
    INDEX
    Explanations

    eliminated in rounds

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

    **

    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
    Negative Logits
     প্রাপ্ত
    0.43
    差
    0.42
    äne
    0.41
     Wieder
    0.40
     Andersen
    0.40
    ơ
    0.40
    勢
    0.39
    élène
    0.39
    지는
    0.39
    褐
    0.39
    POSITIVE LOGITS
    Horizon
    0.48
    Quadrant
    0.46
     idempot
    0.44
    蛐
    0.44
    मारा
    0.43
     मंत्रिम
    0.43
    Categories
    0.42
    ObjectID
    0.42
     quarterfinals
    0.42
    लान
    0.42
    Activations Density 0.000%

    No Known Activations