© 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-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 4527
    Prev
    Next
    INDEX
    Explanations

    technical and structural elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    1.14
     Спорт
    1.09
     Patients
    1.06
     lake
    1.04
     ½
    1.02
     Vì
    1.02
     frutas
    1.01
     Sex
    1.01
     […]
    1.00
     pasien
    1.00
    POSITIVE LOGITS
    Google
    1.00
    Encoding
    0.96
    Executable
    0.94
    Matrix
    0.94
    encoding
    0.93
    HTML
    0.92
    Container
    0.92
    element
    0.92
    Structure
    0.91
    JavaScript
    0.90
    Activations Density 0.136%

    No Known Activations