© 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. 15515
    Prev
    Next
    INDEX
    Explanations

    significant advancement or turning point

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -2.34
    at
    -2.30
    m
    -2.14
    ve
    -2.06
    of
    -2.02
    Étymologie
    -1.96
     erstes
    -1.95
     чем
    -1.84
    どうなる
    -1.84
    ak
    -1.83
    POSITIVE LOGITS
     mereka
    2.48
     να
    2.23
    媪
    2.17
    他們
    2.17
    Ⴀ
    2.13
    ньому
    2.11
    
    2.09
    这两个
    2.08
    CHREIB
    2.08
    čného
    2.06
    Activations Density 0.002%

    No Known Activations