© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2558
    Prev
    Next
    INDEX
    Explanations

    client's lawyer

    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
    wapV
    -0.93
    VPN
    -0.79
    CSRF
    -0.78
    洙
    -0.77
     ¦
    -0.76
    ínű
    -0.76
    anyika
    -0.76
    ![](
    -0.75
    店員
    -0.74
    软件特色
    -0.73
    POSITIVE LOGITS
     clients
    7.47
     client
    7.00
    clients
    5.34
     Clients
    5.34
    client
    5.34
    Clients
    5.16
     Client
    4.72
    Client
    4.53
    CLIENT
    4.25
    客户端
    4.09
    Activations Density 0.099%

    No Known Activations