© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42559
    Prev
    Next
    INDEX
    Explanations

    saying or reminding people of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    縢
    -1.46
     hek
    -1.31
     echt
    -1.29
     ushort
    -1.26
     Leche
    -1.24
    ⩕
    -1.24
    ecznie
    -1.23
    idorm
    -1.20
    varlak
    -1.20
     UserManager
    -1.18
    POSITIVE LOGITS
     that
    2.14
     of
    1.37
    órum
    1.34
     vostre
    1.30
    begin
    1.30
    COHOL
    1.30
    最大的
    1.28
    şan
    1.27
     незавер
    1.27
     つの
    1.24
    Activations Density 0.014%

    No Known Activations