© 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. 4128
    Prev
    Next
    INDEX
    Explanations

    code output

    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
    ithe
    0.77
     thermal
    0.70
     contacted
    0.68
    infeld
    0.67
     length
    0.67
     sapply
    0.66
    recycle
    0.65
     <*>
    0.65
     ביק
    0.64
    rophys
    0.64
    POSITIVE LOGITS
     hasilnya
    1.44
    Результа
    1.31
     risultato
    1.26
     révèle
    1.25
     reveals
    1.24
     resultados
    1.24
     mengungkapkan
    1.16
     revealing
    1.15
     results
    1.14
    Results
    1.14
    Activations Density 0.440%

    No Known Activations