© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128720
    Prev
    Next
    INDEX
    Explanations

    code syntax and keywords

    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
    וּ
    -2.13
    ﻷ
    -2.09
     APPELLANT
    -1.98
    ᾽
    -1.96
    ﻹ
    -1.94
    ﻻ
    -1.92
     DriverManager
    -1.88
    ÈNE
    -1.87
    üyü
    -1.86
    𝔲
    -1.79
    POSITIVE LOGITS
     because
    2.66
    ῖν
    2.27
     Uniwersyte
    1.88
     used
    1.84
     and
    1.82
     победы
    1.82
    ῖς
    1.80
     trying
    1.80
    摂取
    1.80
     had
    1.75
    Activations Density 1.638%

    No Known Activations