© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1339
    Prev
    Next
    INDEX
    Explanations

    subjects and alternatives

    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
     Chiến
    1.37
     Hải
    1.36
    <unused2020>
    1.28
    iftoire
    1.26
     Thị
    1.26
     Faculdade
    1.25
     Hồ
    1.25
     साखर
    1.24
    <unused1465>
    1.23
     Erlebnis
    1.23
    POSITIVE LOGITS
     vs
    1.30
    タイプ
    1.30
    タイプの
    1.22
     versus
    1.17
    または
    1.10
     ou
    1.09
     veya
    1.08
     versi
    1.08
    类型
    1.07
     version
    1.01
    Activations Density 1.594%

    No Known Activations