© 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. 57622
    Prev
    Next
    INDEX
    Explanations

    Apple devices and gadgets

    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
     त्र
    -0.83
    ůli
    -0.81
     hostel
    -0.81
     freer
    -0.81
    zate
    -0.78
    鞋子
    -0.77
    त्र
    -0.77
    gridy
    -0.76
     Viceroy
    -0.75
     OSA
    -0.75
    POSITIVE LOGITS
     iPod
    1.11
     iPhone
    1.05
     iPad
    0.96
     Air
    0.93
     latest
    0.90
     MacBook
    0.90
     original
    0.89
     iMac
    0.87
     seventh
    0.86
     fourth
    0.85
    Activations Density 0.031%

    No Known Activations