© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32983
    Prev
    Next
    INDEX
    Explanations

    limited edition types

    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
    cepteur
    -0.88
     муль
    -0.78
     individuale
    -0.75
     лука
    -0.73
     halus
    -0.72
     canadien
    -0.71
    箪
    -0.71
    bürger
    -0.71
     proj
    -0.70
     syn
    -0.69
    POSITIVE LOGITS
    quier
    0.79
    Disc
    0.76
    イト
    0.75
     lodgings
    0.75
     precedent
    0.73
    寫
    0.71
    溼
    0.70
     momentum
    0.70
     pressed
    0.69
     fortification
    0.69
    Activations Density 0.042%

    No Known Activations