© 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. 113125
    Prev
    Next
    INDEX
    Explanations

    school grades and levels

    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
     свою
    -1.44
    ৬
    -1.30
     bogus
    -1.30
     combineReducers
    -1.29
    総評
    -1.28
    转换
    -1.28
    tit
    -1.27
    赁
    -1.24
     interieur
    -1.23
    谧
    -1.23
    POSITIVE LOGITS
     where
    1.62
     impede
    1.40
     denominada
    1.39
     unveiling
    1.35
    vanced
    1.34
     Kemudian
    1.33
     apoi
    1.32
    boyfriend
    1.31
     Ahor
    1.28
     will
    1.27
    Activations Density 0.027%

    No Known Activations