© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114100
    Prev
    Next
    INDEX
    Explanations

    sold out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    鉝
    -2.30
    淦
    -2.09
    聾
    -2.06
     dañ
    -2.02
     to
    -2.00
    et
    -2.00
     تعدى
    -1.99
    r
    -1.99
    k
    -1.98
    桎
    -1.98
    POSITIVE LOGITS
    狁
    2.39
    虽说
    2.38
     
    2.36
    主に
    2.28
    这也是
    2.20
    錞
    2.19
     Presently
    2.13
    即便
    2.08
    何况
    2.05
     Primarily
    2.05
    Activations Density 0.004%

    No Known Activations