© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2811
    Prev
    Next
    INDEX
    Explanations

    css border properties

    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_22_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
    mmHg
    0.98
    ciju
    0.96
     Usuario
    0.95
    ಹಾರ
    0.94
     puertos
    0.94
    
    0.93
     Encryption
    0.93
     Mathematical
    0.92
    ່ມ
    0.91
    Usuario
    0.91
    POSITIVE LOGITS
    istani
    0.70
     alt
    0.68
     re
    0.67
     no
    0.64
    <em>
    0.64
    fast
    0.61
    altered
    0.61
    이라는
    0.61
     direct
    0.60
     pelas
    0.60
    Activations Density 0.009%

    No Known Activations