© 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. 59104
    Prev
    Next
    INDEX
    Explanations

    REQUESTED information or actions

    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
    mantec
    -0.87
    自杀
    -0.83
    どり
    -0.82
    廝
    -0.81
    剎
    -0.79
     acompañada
    -0.77
     wizy
    -0.76
    說話
    -0.73
     vuotta
    -0.73
     asisti
    -0.73
    POSITIVE LOGITS
    REQUEST
    1.31
     REQUEST
    1.19
    Warnings
    1.12
    Requested
    1.10
    request
    1.10
    requested
    1.04
     imagines
    1.02
    Imagine
    1.00
    Request
    0.99
    Requests
    0.99
    Activations Density 0.004%

    No Known Activations