© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10160
    Prev
    Next
    INDEX
    Explanations

    avoid overcrowding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    t
    3.20
    د
    3.06
    tan
    2.91
    tional
    2.83
    tel
    2.79
    т
    2.71
    tans
    2.60
    tend
    2.57
    tik
    2.55
    tica
    2.54
    POSITIVE LOGITS
    ী
    3.37
    ණය
    2.69
    שט
    2.60
    倜
    2.52
     \|\
    2.51
    _\
    2.44
    ỹ
    2.36
    రుగులు
    2.34
    figcaption
    2.34
    
    2.33
    Activations Density 0.025%

    No Known Activations