© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12732
    Prev
    Next
    INDEX
    Explanations

    what you can control

    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_13_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
     ниж
    1.62
    емость
    1.49
     đơn
    1.44
    ត្
    1.43
     теку
    1.41
     \)
    1.41
     undesirable
    1.41
     也
    1.40
    irregular
    1.40
     다음과
    1.38
    POSITIVE LOGITS
     Nemo
    1.36
     filo
    1.34
    ],"
    1.33
     tanti
    1.27
     liye
    1.26
     Kapoor
    1.26
     apporte
    1.24
     nuclé
    1.23
    ���
    1.22
     camino
    1.22
    Activations Density 0.003%

    No Known Activations