© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7793
    Prev
    Next
    INDEX
    Explanations

    988 lifeline number

    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_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     शाळा
    0.83
    р
    0.83
    ારી
    0.80
    ރ
    0.80
    год
    0.79
    irc
    0.77
    付
    0.77
    acet
    0.72
    jelder
    0.71
    情
    0.70
    POSITIVE LOGITS
    getProduct
    1.09
     huesos
    1.01
     inmig
    1.00
     যোগ্য
    0.97
     cockro
    0.97
     কলের
    0.96
     faktor
    0.96
    ลูกค้า
    0.96
     numquam
    0.96
    accoon
    0.96
    Activations Density 0.020%

    No Known Activations