© 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
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9810
    Prev
    Next
    INDEX
    Explanations

    MD and PhD titles

    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
    responsibility
    0.94
    continu
    0.93
    \
    0.90
    -}
    0.88
     ston
    0.87
     priori
    0.86
    ْ
    0.85
    Peters
    0.84
    ils
    0.83
     responsibility
    0.82
    POSITIVE LOGITS
    了这个
    1.14
    кает
    1.08
    től
    1.07
     һәм
    1.05
     devenue
    0.95
    ো
    0.95
     और
    0.94
    
    0.93
     enlace
    0.92
     avert
    0.91
    Activations Density 0.014%

    No Known Activations