© 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. 220986
    Prev
    Next
    INDEX
    Explanations

    business intelligence; investigative due diligence;

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

    system and data management

    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
     สาม
    0.50
     CharPtr
    0.49
     最后
    0.48
     Dünya
    0.47
    maxY
    0.46
     Bretagne
    0.46
     कैपिट
    0.46
     በ
    0.46
     khác
    0.46
     tartış
    0.46
    POSITIVE LOGITS
     elliptical
    0.55
    pless
    0.51
     motiv
    0.50
     motivations
    0.50
     smelting
    0.50
    添付
    0.50
    ฬ
    0.48
     clarifications
    0.45
    dm
    0.45
     motivating
    0.44
    Activations Density 0.000%

    No Known Activations