© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99127
    Prev
    Next
    INDEX
    Explanations

    "name" attribute or code keywords

    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
     tabs
    -0.92
     tab
    -0.91
    tab
    -0.82
    Tabs
    -0.82
    tabs
    -0.78
     osobow
    -0.75
    креп
    -0.75
     gives
    -0.71
     Erfindung
    -0.71
     Alexa
    -0.70
    POSITIVE LOGITS
    vaal
    0.75
     getGroup
    0.75
    brokers
    0.73
     دیکھیے
    0.73
    kaa
    0.72
    ️⃣
    0.71
    ったら
    0.71
     elevación
    0.70
    \",\"
    0.70
     alms
    0.70
    Activations Density 0.020%

    No Known Activations