© 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. 56847
    Prev
    Next
    INDEX
    Explanations

    non-English words and specific terms

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

    efficiency and respect

    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
    젹
    0.46
     exploited
    0.44
     smatra
    0.44
     sa
    0.44
    க்
    0.43
     reveals
    0.43
    LSTM
    0.43
     consisted
    0.43
    ı
    0.43
     says
    0.43
    POSITIVE LOGITS
    移
    0.47
    Cemento
    0.47
     मूल
    0.45
     철
    0.45
     重量
    0.45
     武田
    0.45
     เด่น
    0.43
    鉄
    0.43
    paralle
    0.43
     スチール
    0.43
    Activations Density 0.000%

    No Known Activations