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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9575
    Prev
    Next
    INDEX
    Explanations

    stand and context

    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
    Not in Any Lists

    No Comments

    Negative Logits
    𝗼
    2.08
     спорттук
    2.08
     ö
    2.07
    WindowEvent
    2.06
    incorporated
    2.05
    ouml
    2.04
    uuml
    2.03
    𝗺
    1.97
    öl
    1.96
    𝗵
    1.91
    POSITIVE LOGITS
    semer
    2.27
     nigra
    2.04
    कोण
    1.92
    การณ์
    1.89
    caster
    1.89
    闘
    1.86
    āv
    1.83
    st
    1.83
    fecture
    1.81
    วะ
    1.80
    Activations Density 0.106%

    No Known Activations