© 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. 4157
    Prev
    Next
    INDEX
    Explanations

    Tum, silicon, proteins, turning

    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
    ᠰ
    3.03
    ---------
    2.88
    itaea
    2.79
    𝘃
    2.78
    𝗴
    2.78
     एजु
    2.76
    
    2.75
    ᠴ
    2.74
    𝗨
    2.74
    -----------
    2.73
    POSITIVE LOGITS
    ের
    3.05
    y
    2.57
    se
    2.52
    u
    2.32
    ي
    2.30
    an
    2.20
    ا
    2.11
    te
    2.02
    ar
    2.01
    ों
    1.99
    Activations Density 0.006%

    No Known Activations