© 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. 119905
    Prev
    Next
    INDEX
    Explanations

    whether how that to

    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
     it
    -1.29
    Just
    -1.24
     just
    -1.23
     occurring
    -1.20
     resembling
    -1.16
    //
    -1.13
     wanting
    -1.09
    ของ
    -1.09
     and
    -1.09
     ešte
    -1.06
    POSITIVE LOGITS
     Jazeera
    1.30
    面色
    1.27
     cuarent
    1.22
     menyukai
    1.17
    ногие
    1.16
     nuevos
    1.16
     outono
    1.15
    zyński
    1.14
    </h3>
    1.11
    these
    1.09
    Activations Density 0.118%

    No Known Activations