© 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. 31191
    Prev
    Next
    INDEX
    Explanations

    push pop stack operations

    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
    ARIA
    -0.85
     celana
    -0.85
    ⌓
    -0.83
    请输入
    -0.83
    ços
    -0.82
    ्रिया
    -0.80
    ℭ
    -0.79
    zember
    -0.78
    Noticia
    -0.78
     sham
    -0.78
    POSITIVE LOGITS
    push
    1.16
     push
    1.15
     of
    0.94
    pop
    0.93
     pushed
    0.89
     pushing
    0.89
     pop
    0.88
     Push
    0.87
    Push
    0.86
     pushes
    0.84
    Activations Density 0.001%

    No Known Activations