© 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. 19379
    Prev
    Next
    INDEX
    Explanations

    nicknames and first 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
     another
    -1.52
    等到
    -1.45
     resultó
    -1.32
    another
    -1.31
     tendremos
    -1.27
     desplie
    -1.27
     inny
    -1.27
    iniques
    -1.26
     extremely
    -1.23
    另一
    -1.22
    POSITIVE LOGITS
     also
    1.61
     from
    1.60
     with
    1.39
     också
    1.38
     myös
    1.37
     endast
    1.31
     باید
    1.30
    Мекси
    1.30
     började
    1.30
     dessutom
    1.30
    Activations Density 0.116%

    No Known Activations