© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4618
    Prev
    Next
    INDEX
    Explanations

    bolded key terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    নির্ব
    0.72
     -
    0.72
     -----
    0.69
    щиеся
    0.68
    替え
    0.68
       
    0.68
    cele
    0.67
     -------
    0.66
    º
    0.65
    રે
    0.64
    POSITIVE LOGITS
    Consequently
    0.90
     flavon
    0.88
    Nonetheless
    0.88
     hasattr
    0.87
    ள்ளதாக
    0.87
     farmac
    0.86
    estream
    0.85
     Consequently
    0.84
     imponer
    0.84
     zahlreichen
    0.82
    Activations Density 0.089%

    No Known Activations