© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89860
    Prev
    Next
    INDEX
    Explanations

    successor to or currently available

    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
     blir
    -1.00
     vehicle
    -0.98
     nastro
    -0.97
    🪳
    -0.95
     restaurant
    -0.92
     ricas
    -0.91
     Sobald
    -0.91
    gör
    -0.91
     передний
    -0.90
    〉
    -0.90
    POSITIVE LOGITS
     device
    1.48
     devices
    1.34
     Android
    1.32
    device
    1.27
     vanil
    1.26
     DEVICE
    1.23
     hardware
    1.20
     flagship
    1.20
    Device
    1.19
     consumers
    1.16
    Activations Density 0.074%

    No Known Activations