© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10792
    Prev
    Next
    INDEX
    Explanations

    create Windows Forms

    np_acts-logits-general · gemini-2.5-flash-lite

    Project setup and build commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nay
    0.39
    ury
    0.39
    ый
    0.37
     Colón
    0.37
     Fock
    0.36
     quell
    0.36
     |_{
    0.36
     Pont
    0.36
     Leh
    0.36
    <0x8F>
    0.35
    POSITIVE LOGITS
    buildSpec
    0.55
     문자
    0.49
     природе
    0.45
    InputDir
    0.44
    javab
    0.44
    Ave
    0.43
     creazione
    0.42
    创建
    0.41
    人性
    0.40
    Buildable
    0.40
    Activations Density 0.005%

    No Known Activations