© 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. 12993
    Prev
    Next
    INDEX
    Explanations

    call me / war / divide / sum

    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
    -​
    1.06
     immediacy
    0.97
     रॉयल
    0.97
    ღ
    0.94
     extravagance
    0.94
    ──────
    0.93
    方案
    0.90
    廣告
    0.90
    -
    0.89
     academ
    0.88
    POSITIVE LOGITS
    ták
    1.36
     ব্যাক্ত
    1.28
    nagyobb
    1.28
    jenje
    1.26
     !!,
    1.26
    nungen
    1.25
    iqi
    1.23
    みると
    1.21
    iť
    1.21
    jera
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.