© 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. 85594
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

    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
     in
    -1.77
     them
    -1.61
     it
    -1.59
     with
    -1.47
     not
    -1.45
     itself
    -1.44
     كافة
    -1.42
    ,
    -1.40
     chargeur
    -1.34
     آنها
    -1.32
    POSITIVE LOGITS
     Había
    1.37
     previous
    1.34
    }
    1.32
     cuestiones
    1.31
    rafat
    1.29
    菑
    1.29
    carteles
    1.27
    赑
    1.26
    ৄ
    1.25
     некоторы
    1.23
    Activations Density 0.005%

    No Known Activations