© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12323
    Prev
    Next
    INDEX
    Explanations

    such as / e.g

    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
    <bos>
    3.61
    ں
    2.94
    しよう
    2.87
    LESS
    2.87
    ୍ୟ
    2.81
    ภัณฑ์
    2.80
    ৫
    2.77
    してい
    2.75
    ñada
    2.74
    UNION
    2.71
    POSITIVE LOGITS
    了
    3.75
    nya
    3.65
    st
    3.55
    rd
    3.48
    م
    3.37
    다고
    3.28
    ことができます
    3.28
    ้ํา
    3.25
    sonsten
    3.24
    ことができる
    3.21
    Activations Density 0.355%

    No Known Activations