© 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. 77178
    Prev
    Next
    INDEX
    Explanations

    connection urls and details

    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
     firestore
    -0.79
    alucía
    -0.75
     čier
    -0.71
     vitaminas
    -0.70
    olverine
    -0.69
     Stanford
    -0.68
    ЭС
    -0.68
    וס
    -0.68
    Stanford
    -0.68
     schwarzen
    -0.68
    POSITIVE LOGITS
     url
    2.58
     URL
    2.47
    url
    2.39
    URL
    2.20
    Url
    2.17
     host
    1.85
     address
    1.84
     Url
    1.80
     URLs
    1.79
    地址
    1.77
    Activations Density 0.186%

    No Known Activations