© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1249
    Prev
    Next
    INDEX
    Explanations

    reporting officials and sources

    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_29_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
    優秀
    0.69
    ăr
    0.69
    Globalization
    0.68
    importanza
    0.68
     দরকার
    0.67
    Answer
    0.67
    Importance
    0.65
    <unused1087>
    0.64
    Provides
    0.64
     इंपॉर्ट
    0.64
    POSITIVE LOGITS
     reports
    2.18
     reportedly
    1.86
    reports
    1.81
     according
    1.79
     Reports
    1.78
     officials
    1.68
     sources
    1.67
    Reports
    1.67
     allegedly
    1.63
    according
    1.60
    Activations Density 0.318%

    No Known Activations