© 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. 34-GEMMASCOPE-RES-131K
    7. 64222
    Prev
    Next
    INDEX
    Explanations

    installing software packages

    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_34/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
    innerHeight
    -0.96
    Ή
    -0.87
    {
    -0.86
    IGF
    -0.84
    UNTS
    -0.83
    ilities
    -0.82
    🅘
    -0.82
    titleMargin
    -0.81
    pherals
    -0.78
    ೫
    -0.78
    POSITIVE LOGITS
     Java
    1.40
     JDK
    1.34
     Python
    1.19
    JDK
    1.17
     java
    1.13
     latest
    1.13
     python
    1.11
    jdk
    1.09
    Java
    1.07
     prerequisites
    1.04
    Activations Density 0.132%

    No Known Activations