© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6150
    Prev
    Next
    INDEX
    Explanations

    empty or missing values

    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
    backgroundSplit
    2.21
    redos
    2.02
    াউ
    1.93
    𝗼
    1.93
    𝐨
    1.90
    棘
    1.89
     Temos
    1.86
    ếp
    1.86
    AGT
    1.83
    𝘂
    1.82
    POSITIVE LOGITS
    <bos>
    2.31
    =’
    2.03
    ia
    1.96
     Архивировано
    1.96
    싹
    1.92
    짠
    1.90
    ”)
    1.89
     солнца
    1.84
     заключа
    1.84
    ”
    1.82
    Activations Density 0.111%

    No Known Activations