© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10852
    Prev
    Next
    INDEX
    Explanations

    people's last names

    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
     addition
    -1.26
     as
    -1.21
     rainforest
    -1.17
     اینجا
    -1.15
     added
    -1.15
     ebenso
    -1.13
    блица
    -1.10
     doar
    -1.08
    lazione
    -1.07
     by
    -1.06
    POSITIVE LOGITS
     demostr
    1.23
    .~\
    1.19
    ఱ
    1.18
    certainly
    1.18
    allowed
    1.16
    mola
    1.15
    ⁸
    1.15
     самые
    1.15
    {{--
    1.13
     damski
    1.13
    Activations Density 0.168%

    No Known Activations