© 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. 58355
    Prev
    Next
    INDEX
    Explanations

    must be or have

    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
    蛧
    -1.47
    我們
    -1.46
    萏
    -1.43
    کیف
    -1.39
     personnalisées
    -1.38
     we
    -1.37
    なりません
    -1.36
     Unternehmer
    -1.36
     is
    -1.34
    دوست
    -1.32
    POSITIVE LOGITS
     kteří
    1.56
    もの
    1.55
     geeigne
    1.52
     kellett
    1.43
    EdgeInsets
    1.37
    kabau
    1.36
     schwarze
    1.34
    setEmail
    1.33
     feinen
    1.31
    察觉
    1.31
    Activations Density 0.022%

    No Known Activations